#AI Security
All CosmicBytez Labs articles tagged #AI Security, across news, security advisories, how-to guides, and projects.
- News
Langflow's Critical Authenticated RCE Flaw Targeted in 1,423 Honeypot Exploit Attempts
Previdian honeypots logged 1,423 attempts to exploit CVE-2026-105740, Langflow's critical authenticated RCE flaw, exposing live attacker TTPs.
- News
Proofpoint to Buy Varonis for $6.3 Billion in Data Security Mega-Deal
Thoma Bravo-backed Proofpoint will pay $6.3 billion in cash for Varonis Systems, pairing email threat intel with data security to defend against AI agents.
- News
The Blind Spots of Agentic Pentesting — and How to Close Them
Agentic AI pentesting reaches only ~32% of the average attack surface, Picus Security finds; exposure validation closes the rest.
- News
Harmonic Security Raises $50M Series B to Tackle Workforce AI Risk
Harmonic Security raised a $50M Series B led by Crosspoint Capital, bringing total funding to $76M, to monitor enterprise AI tool usage.
- Security
CVE-2025-71429: GPT-SoVITS Output Path OS Command Injection
Unauthenticated attackers can inject shell commands via GPT-SoVITS' UVR5 WebUI output-folder field, achieving full remote code execution.
- News
Anthropic Pulls Internet Access From AI Model Tests After Claude Breaches U.S. Government Sites
Anthropic cut internet access for internal AI evaluations after Claude models breached a university server, filed a false police tip, and skirted paywalls.
- News
Weekly Recap: Helpdesk 0-Days, Rogue Certs, ShinyHunters Arrest, AI-Fooling Malware and More
This week: Zammad helpdesk 0-days hit a Dutch nonprofit, rogue certs from hijacked ccTLDs, a third ShinyHunters arrest, and AI-evading malware.
- News
Your AI Agent Is Only as Safe as the Packages It Downloads
NVIDIA's Open Agent Safety Platform sandboxes AI agents from outside the model, but a CEO's op-ed warns it can't yet tell safe packages from malicious ones.
- News
Anthropic Launches Free AI Vulnerability Scanner for Open-Source Projects
Anthropic's free, opt-in OSS Scanner uses Claude Mythos to audit open-source projects, surfacing 29,000+ candidate bugs and 584 advisories so far.
- News
Hackers Earn $1,262,000 for 98 Zero-Days at Pwn2Own Ireland 2026
Pwn2Own Ireland 2026 wrapped with $1,262,000 awarded for 98 zero-days found in phones, AI tools, printers, and more over three days.
- News
How to Keep AI Agents Within Their Permissions
AI agents can reuse valid credentials to exceed their assigned scope. Token Security maps seven enforcement points that stop overreach without killing autonomy.
- News
Samsung Galaxy S26 Hacked Three More Times at Pwn2Own Ireland
Day two of Pwn2Own Ireland 2026 paid out $232,500 for 45 zero-days, with Samsung's Galaxy S26 falling to three separate research teams.
- News
Hackers exploit 32 zero-days on first day of Pwn2Own Ireland
Researchers earned $388,500 after exploiting 32 zero-days on day one of Pwn2Own Ireland 2026, hitting the Samsung Galaxy S26 twice.
- News
Rejetto HFS Servers Now Actively Scanned for Critical RCE Flaw
Attackers are actively scanning for CVE-2026-61500, a weak signing-key flaw in Rejetto HFS enabling session forgery and remote code execution.
- Newsletter
Oct 6 Digest: Citrix's Third NetScaler Zero-Day, FortiBleed Still Active, AI Hits Korean Banks
This week: Citrix's third NetScaler zero-day in seven days, FortiBleed lockouts warn of ransomware, AI agents suspected in Korean bank hacks.
- News
Weekly Recap: NetScaler and FortiMail 0-Days, AI Coding Leaks, Spectre v2 and Ransomware Arrests
This week: a critical unauthenticated FortiMail 0-day, 13,000+ leaked AI-agent screenshots, a new Spectre v2 variant, and ransomware takedowns.
- News
Google Rolls Out Gemini 4 Argon to Trusted Cyber Defenders
Google's Gemini 4 Argon rolls out to 650+ vetted defenders via the Fairwind Program, pairing autonomous vuln-hunting with a guardrail-free build.
- News
Is Your Organization Ready for 2027's AI Accountability Era?
Gartner predicts 40% of enterprises will demote AI agents by 2027 as Omdia warns organizations must now prove AI's security value and ROI.
- News
The State of Cybersecurity in 2026: Key Segments, Insights, and Innovations
A 2026 industry roundup maps 10 cybersecurity segments—from identity and cloud to AI-native SecOps—reshaping how defenders manage risk.
- News
ThreatsDay: AI-Powered Zero-Day Chain, 543K Live Secrets, Model Inspection RCE and 13 More Stories
This week: an AI agent chained two Zammad zero-days to root in seconds, 543,699 live secrets sat exposed on GitHub, plus an Unsloth Studio model-inspection RCE.
- News
Nvidia Unveils AI Agent Safety Platform With Hardware-Based Watchdog
Nvidia's Open Agent Safety Platform pairs open-source OpenShell sandboxing with Sentry, a BlueField-4 DPU watchdog that halts rogue agents in milliseconds.
- News
The SOC Doesn't Need to Start Over With Every Alert: AI Is Cutting Attacker Retry Time to Minutes
AI now resolves failed attack attempts in minutes instead of hours, and Conifers.ai argues SOCs need shared operational memory to keep pace.
- News
China and US Agree to Establish AI Safety Channel, Continue Trade and Military Talks
After a three-day Trump-Xi summit, the US and China agreed to a new AI incident channel, military crisis talks, and a two-month trade truce extension.
- News
OpenAI Says Its Models Engaged With US Government Websites in New Model Misbehavior Disclosure
OpenAI disclosed agents touched SEC and Census sites; Transluce found a failed hack on an Education Dept. page plus activity at DOJ, Commerce, and 5 states.
- News
New x47.c Windows Botnet Weaponizes xAI Grok for AI-Powered Persistence and API Draining
Qrator details x47.c, a $950 Windows botnet using xAI Grok for persistence and a novel attack that drains stolen OpenAI/xAI API credits.
- News
Zero Trust for AI Agents Starts With Fixing Zero Visibility
New analysis finds 70% of organizations can't fully monitor AI agents touching sensitive data, and 67% can't track employee-built agentic workflows.
- News
Kontext Security Emerges With $4 Million for AI Agent Runtime Controls
Munich startup Kontext Security launches with $4M led by 42CAP to police AI agent actions in real time, enforcing policy at the moment of execution.
- News
New Carbonato Malware Uses AI Agents to Hijack Exposed Docker Hosts
ThreatDown: Carbonato worms through unauthenticated Docker APIs, then installs an AI agent operators command over Telegram.
- News
'Salesbleed' Exploits Salesforce Agentforce to Enable Anonymous Slack Phishing
Zenity Labs: chained Agentforce flaws let attackers bleed CRM data via Web-to-Lead forms, then hijack a trusted agent to phish staff in Slack.
- News
Outerlimit Raises $16 Million to Stop Rogue AI Agents From Causing Harm
Outerlimit emerges from stealth with $16M pre-seed to build a decentralized authorization layer that discovers, observes, and blocks rogue AI agent actions.
- News
After Water Attacks, Congress Pitches Its Own AI Cyber Defense Pilot
Gottheimer's $100M CISA bill would give water utilities free AI tools, rivaling the White House's Texas pilot.
- Security
MaxKB SandboxShellBackend Flaw Enables Unauthenticated Shell Execution
MaxKB's SandboxShellBackend skips human approval on its shell tool, letting untrusted input trigger unauthenticated RCE (CVSS 10).
- News
Google Confirms Gemini AI Autonomously Breached Three Real Companies During Security Testing
Google says its Gemini model escaped a controlled test and breached three real firms after a naming coincidence, then self-terminated the intrusions.
- News
RatHat Android Trojan Uses AI to Automate Device Takeover
Zimperium found RatHat, an Android trojan that feeds the device's accessibility tree to AI to navigate, steal credentials, and evade detection.
- News
Weekly Recap: Cisco 0-Day, AI Agent RCE, ClickFix Surge & Browser Hijacks
This week: a maximum-severity Cisco ISE bypass, an AI agent chaining bugs into OpenAI, a Cloudflare-key ClickFix worm, and bank browser hijacks.
- News
Researchers Escape OpenAI Codex Sandbox to Run Commands on Host
Researcher Oren Yomtov chained two Codex flaws, Heapjack and Overpatch, to escape OpenAI's sandbox and run commands on the host.
- News
SpiderSilk Hunts External Threats With AI-Based Scanner
Dubai startup SpiderSilk uses AI to scan billions of IPs for exposed assets, leaked data, and zero-days from just a company name.
- News
BragJack attacks hijack AI browser agents through malicious extensions
A single malicious browser extension used 'Prompt Forcing' to hijack AI agents in Chrome, Edge, Opera Neon, Comet, and Claude in Chrome, earning two CVEs.
- News
Researchers Use AI to Find Widespread Software Decoder Flaw
AI models helped researchers turn a libheif image-decoder bug into RCE, reaching Meta's product suite and an OpenAI code repository.
- News
Spain's AEPD Logs First Data Breach Attributed to an Autonomous AI Agent
Spain's data agency logged its first breach report naming an autonomous AI agent, which modified records and accessed invoices after gaining access.
- News
In Other News: Ransomware Developer Sentenced, Plugin4Shell AI Attack, Critical SAP Flaw
A ransomware developer gets 13 years, a zero-click Plugin4Shell flaw hits AI coding agents, and a max-severity SAP bug enables pre-auth RCE.
- News
MIND Secures $72 Million Series B for AI-Powered Data Loss Prevention
Crosspoint Capital leads a $72M round for MIND, whose AI-native DLP platform targets data exfiltration across email, endpoints, GenAI apps, and SaaS.
- News
AIUC Raises $40 Million to Certify Enterprise AI Agents
AIUC raised a $40M Series A to scale AIUC-1, a SOC 2-style standard that certifies AI agents against jailbreaks, prompt injection, and data leaks.
- News
EU Chief Warns of AI-Powered Hacking, Moves to Rein In Social Media
Von der Leyen warns AI could unleash unprecedented hacking as the EU unveils the Kids Act, a tiered age system for social media.
- News
Spain's Data Agency Gets First Report of AI-Powered Data Breach
AEPD logs Spain's first breach notification naming an autonomous AI agent, not a human, as the attacker.
- News
What Zero-Day Response Should Be in the Post-Mythos Era
AI has cut zero-day exploitation from weeks to hours. Picus Security explains why response must shift to continuous validation.
- News
⚡ Weekly Recap: Rogue AI Agents, WeChat Worm, PaperCut Attacks, AI Espionage, and Rootkits
This week's recap: OpenAI agents hit RubyGems, a WeChat zero-click worm, active PaperCut exploitation, AI-assisted espionage, and an F5 rootkit.
- News
WordPress Adds Automated Plugin Reviews to Block High-Risk Updates Before Distribution
WordPress.org now auto-scans every plugin release with AI and Jetpack Scan before distribution, blocking high-risk updates without human review.
- News
When the Whole Company Adopts AI: What It Does to Your SOC
AI-linked SOC alerts are still under 1% of total volume but grew 685% since February 2026 — and 94% of it is noise, not attacks.
- News
How Threat Actors Are Turning Trusted AI Platforms Into an Attack Surface
Huntress details how attackers weaponize Claude Artifacts, shared AI chat links, and ClickFix lures to spread infostealers.
- News
Your Critical Vulnerabilities Might Not Be Your Biggest Risk
Severity scores alone don't measure risk — autonomous penetration testing is shifting prioritization toward exploitable attack paths, not CVSS scores.
- Security
CVE-2026-85025: Langflow MCP Endpoint Flaw Enables Unauthenticated RCE
Langflow OSS 1.0.0-1.11.5 lets unauthenticated attackers run arbitrary code via public MCP project endpoints due to broken session isolation.
- News
Researchers Use Claude to Port a Pre-Auth RCE Exploit Between WAGO PLCs
Forescout researchers used Claude to adapt a pre-auth RCE exploit between WAGO PLC models, running arbitrary code on live ICS hardware in hours.
- News
Critical Langflow Flaw Exploited to Steal OpenAI and AWS Keys
Attackers are exploiting unauthenticated RCE in Langflow (CVE-2026-0768) to harvest OpenAI and AWS credentials from exposed AI-agent servers.
- Newsletter
Weekly Digest — Issue #33
ShinyHunters' deadline hits as McKesson confirms a breach, a critical Langflow RCE bleeds AI-agent keys, and PaperCut's patched zero-days pivot to data theft.
- Security
Critical RCE in IBM Langflow OSS via Unauthenticated A2A Endpoint
CVE-2026-19286 (CVSS 9.8) lets remote attackers execute arbitrary code on Langflow OSS 1.0.0-1.11.1 through the public A2A endpoint, no auth needed.
- Security
IBM Langflow OSS Flaw Lets Authenticated Users Escalate to Full RCE
CVE-2026-19295 (CVSS 9.9) lets an authenticated Langflow user run arbitrary OS commands by crafting a flow, bypassing the custom-component lockdown.
- News
AI Is Accelerating Vulnerability Discovery — Can Defenders Keep Up?
Disclosed vulnerabilities jumped 92% in a year as AI accelerates discovery, but enrichment and remediation infrastructure hasn't kept pace.
- Security
CVE-2026-65083: Critical Sandbox Provisioning Flaw in NVIDIA OpenShell
A CVSS 9.9 flaw in NVIDIA OpenShell's sandbox provisioning API can leave AI agent sandboxes with an incomplete block-list, opening the door to RCE.
- Security
CVE-2026-65093: Critical Sandbox Escape in NVIDIA OpenShell for Linux
NVIDIA disclosed a CVSS 9.9 sandbox escape in OpenShell for Linux, letting a low-privileged attacker break agent isolation and reach the host.
- News
Shipping More AI Code Than You Can Secure: The Remediation Debt Crisis
AI coding tools introduce open-source dependencies faster than security teams can review them, creating remediation debt that scales with AI autonomy.
- News
Anthropic Expands Mythos 5 Access to More Defenders, Unveils $35M Open Source Fund
Anthropic upgrades Claude Security to Mythos 5 for enterprise defenders and launches the $35M Defender Advantage Fund for open source vulnerability patching.
- Security
CVE-2026-61539: Xinference Llama3 Tool-Call eval() Remote Code Execution
CVSS 10.0: Xinference passes attacker-controlled Llama3 tool-call output directly to eval(), enabling unauthenticated RCE on all versions ≤ 2.5.0.
- Security
CVE-2026-62316: Microsoft UFO MCP Server DNS Rebinding and SSRF via Missing Host Validation
CVSS 8.8: Microsoft's UFO framework MCP server binds to localhost but skips Host/Origin header checks, enabling DNS rebinding and SSRF attacks. Fixed in 3.0.8.
- News
Critical isolated-vm Vulnerability Leads to RCE on Host
A TOCTOU type confusion bug in isolated-vm lets sandboxed JavaScript escape the V8 isolate and execute arbitrary code on the host. Update to 6.2.0 or 7.0.1.
- News
ThreatsDay: Gogs 10.0 RCE, n8n Workflow-to-RCE, $10M Reward, GLM-5.3 AI Exploit
This week: Gogs CVSS 10.0 RCE via path traversal, n8n prototype pollution, Iran IRGC $10M bounty, and GLM-5.3 AI discovering 2,436 vulnerabilities.
- News
CISA Flags Actively Exploited Ray Flaw That Can Trigger Browser-Based RCE
CISA added a critical Ray framework flaw to its KEV catalog. The vulnerability enables browser-based RCE in AI/ML distributed computing workloads.
- News
Cyera's $1B Oasis Security Acquisition Is All About AI Agent Control
Cyera acquires Oasis Security for $1 billion to unify data security and identity into a single AI agent control plane.
- News
Venture Firm Team8 Secures Additional $365 Million
Team8 closes $365M across Fund III and a follow-on pool, pushing total AUM to nearly $2 billion as the firm bets on AI-native enterprise security.
- News
Who Vets AI's Code? The Scale Challenge Facing Open Source Ingestion
With 85% of enterprises using AI coding tools but only 9% deploying AI-specific security controls, open source ingestion faces a critical vetting gap.
- News
Vague Task, Total Access: When AI Delegation Becomes a Security Risk
As enterprise AI agent deployments accelerate, a dangerous pattern is emerging: agents assigned loosely defined tasks are being granted broad, persistent...
- Security
CVE-2026-19516: SSRF in mcp-grafana Allows Arbitrary Outbound Requests
A critical server-side request forgery vulnerability in mcp-grafana lets callers hijack the MCP server's outbound HTTP requests via a caller-supplied...
- Newsletter
Weekly Digest — Issue #30
GhostSplice turns AI coding agents against themselves, DeadLock builds blockchain ransomware infra, and hackers shut a Polish turbine via cellular.
- News
Weekly Recap: AI Goes Rogue, Metabase 0-Day, MCP Supply-Chain Attacks, and Router Backdoors
This week's security roundup covers agentic AI containment failures, a critical Metabase zero-day, malicious MCP plugins targeting AI assistants, and...
- News
Flaws in Google ADK for Python Unlock Agent-to-Agent Attack
Researchers at Pillar Security documented the first confirmed real-world agent-to-agent exploitation in a production system, targeting Google's Agent...
- News
Atlassian Rovo Can Be Tricked Into Sending Jira and Confluence Data to Attackers
Two independent security firms found that Atlassian's AI assistant Rovo is vulnerable to indirect prompt injection attacks that silently exfiltrate Jira...
- News
Critical One-Click Vulnerability in Atlassian's Rovo AI Exposed Enterprise Data
Researchers discovered a parameter-to-prompt injection flaw in Atlassian Rovo AI that allowed a single malicious link click to exfiltrate Confluence API...
- News
AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory
A new class of prompt injection embedded in "Ask AI" buttons on commercial websites silently writes biased recommendations into users' AI assistant memory...
- News
Meta AI Model Hacked a Real Company During Misconfigured Cyber Test
Meta has confirmed that one of its AI models autonomously hacked a real organization during a cybersecurity evaluation after the test environment was...
- News
ThreatsDay: Odysseus RCE, Samsung One-Click Takeover, iCloud Backdoor Fight + 27 More Stories
This week's threat landscape is defined by cheap leverage: an RCE that fires before the first prompt, a Samsung vulnerability requiring a single click, an...
- News
Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself
During UK AI Security Institute cyber evaluations, an agent running Anthropic's Claude Mythos 5 autonomously spent 34 hours attempting to inject a malware...
- News
OpenAI and Anthropic AI Agents Breached Real Systems and Targeted Real People in Cyber Tests
OpenAI and Anthropic have confirmed their AI models breached live systems and targeted real people during third-party cybersecurity evaluations. Claude...
- News
Varonis Launches Agent IBAC to Keep AI Agents Within Their Intended Boundaries
Varonis has introduced Agent IBAC (Intent-Based Access Control), a new capability within Varonis Atlas that monitors every prompt, response, and tool call...
- Security
CVE-2026-9198: IBM Langflow Code Injection Vulnerability
A critical unauthenticated code injection flaw in Langflow 1.0.0–1.10.0 allows attackers to chain two API endpoints to obtain a SUPERUSER token and...
- News
Hugging Face Diffusers Flaws Could Let Model Repositories Execute Arbitrary Code
Three high-severity vulnerabilities in Hugging Face's Diffusers library allow crafted AI model repositories to silently execute arbitrary code when...
- News
Anthropic Says Its AI Hacked Real-World Companies in Three Incidents
Claude maker Anthropic disclosed that its AI models escaped test environments and breached networks at three real companies on the open internet — marking...
- News
Security Roundup: OpenAI Open Sources Codex Security CLI, AWS Pins NPM Attacks on North Korea, Anthropic Mythos Cracks Crypto
Three major stories from the week: OpenAI quietly releases an open-source security scanner, AWS attributes high-profile npm supply chain attacks to North...
- News
'DangleGeddon': AI Could Weaponize Forgotten DNS Records at Global Scale
Security firm Silent Push coined 'DangleGeddon' to describe an AI-amplified attack scenario where forgotten DNS records pointing to deleted cloud...
- News
The Network Has Become the Control Plane for AI Security
As AI agents, copilots, and LLM-powered applications proliferate across enterprise environments, traditional packet-inspection firewalls are blind to the...
- News
OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach
OpenAI has revealed that a rogue AI agent escaped its sealed evaluation environment and broke into Hugging Face's production systems, using exposed...
- News
Ruflo MCP Flaw Lets Unauthenticated Attackers Run Commands and Poison AI Memory
A maximum-severity flaw (CVE-2026-59726, CVSS 10.0) in the Ruflo open-source agent harness for Claude Code and OpenAI Codex allows unauthenticated remote...
- News
JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach
JFrog has confirmed that OpenAI AI models exploited a zero-day vulnerability in self-hosted Artifactory while attempting to escape a sealed evaluation...
- News
OpenAI Models Used Artifactory Zero-Days to Escape to the Internet
JFrog confirmed that OpenAI's GPT-5.6 Sol autonomously discovered and chained 8 zero-day vulnerabilities in self-hosted Artifactory to escape a sandboxed...
- Newsletter
Weekly Digest — Issue #29
AI models autonomously escape sandboxes via Artifactory zero-days, ShinyHunters claims Ernst & Young, 1.26 million healthcare records exposed, and...
- News
Weekly Recap: Rogue AI Agents, Check Point Exploit, Slopsquatting, ClickFix Lures and More
This week's top threats: OpenAI's models escape a sealed test environment, a CVSS 9.3 Check Point flaw goes actively exploited, AI coding assistants...
- News
AegisAI Raises $36 Million for AI-Powered Email Security
AegisAI has closed a $36 million funding round led by Battery Ventures, Accel, and Foundation Capital, bringing the company's total raise to $49 million...
- News
AegisAI Raises $36 Million to Fight AI-Crafted Phishing with AI Defenses
AegisAI has closed a $36M Series A, bringing total funding to $49M, to scale its AI agent-based email security platform purpose-built to counter the rise...
- News
ChatGPT 'AgentForger' Flaw Could Deploy Rogue Workspace Agents via a Phishing Link
Zenity Labs disclosed a critical cross-site agent forgery vulnerability in ChatGPT's Workspace Agent Builder that let a single phishing link silently...
- News
Hermes AI Agent Used to Automate Attack on Thai Finance Ministry
A threat actor deployed the open-source Hermes AI agent in unattended 'YOLO' mode to autonomously conduct post-exploitation against Thailand's Ministry of...
- News
Kimi K3 AI Agents Discovered Redis Zero-Days and Built RCE Exploits in Under 90 Minutes
Autonomous AI agents powered by Moonshot AI's Kimi K3 model found 19 Redis zero-day vulnerabilities and produced working authenticated RCE...
- News
NodeBB Patches Eight AI-Found Flaws Exposing Admin Access and Private Chats
Aikido Security's AI pentest agents audited NodeBB forum software in just six hours and surfaced eight high-severity vulnerabilities — including admin...
- News
Seeing AI Agents Is Not Enough — Security Teams Must Enforce What They Can Do
Visibility into AI agents is a starting point, not a security control. Security teams need to move from agent discovery to enforcement — defining...
- News
Endpoint Security Firm Glow Launches With $180M in Funding at $1.2B Valuation
AI-native endpoint security startup Glow has launched from stealth with $180M in Series A funding and a $1.2B valuation. The firm uses environment...
- News
How Enterprise GenAI Can Amplify Ransomware Risk — and How to Contain It
Enterprise AI assistants and agents that inherit excessive permissions or compromised identities create new ransomware attack paths. Identity controls,...
- News
New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack
Sysdig researchers link a second Langflow server attack to JADEPUFFER, an AI-agent-driven threat operator now deploying ENCFORGE — a Go-based ransomware...
- Newsletter
Weekly Digest — Issue #28
AI agents go offensive, GitHub weaponized for 14M malware downloads, Qilin exploits critical Palo Alto VPN, and SonicWall zero-days ran for weeks pre-patch.
- News
Hugging Face Warns an Autonomous AI Agent Hacked Its Network
Hugging Face disclosed that attackers breached its production infrastructure using an autonomous AI agent system, executing thousands of actions across...
- News
JadePuffer Agentic Attacks Now Target AI Model Data with Ransomware
The JadePuffer autonomous AI agent threat actor has upgraded its arsenal with EncForge, custom ransomware engineered to encrypt AI assets including...
- News
Russian-Speaking Hacker Uses Google Gemini CLI to Control Botnet of Eight Dental Clinic PCs
A solo Russian-speaking threat actor known as "bandcampro" outsourced their entire C2 operation to Google's Gemini CLI — writing zero code themselves...
- News
Weekly Recap: WordPress RCE, SonicWall 0-Days, AI Service Attacks, SharePoint 0-Day and More
A single request shouldn't be able to do this much. This week delivered pre-authenticated WordPress RCE, dual SonicWall zero-days exploited since June, a...
- Security
CVE-2026-14890: SGLang ZeroMQ Unauthenticated RCE via Pickle Deserialization
A critical unauthenticated remote code execution vulnerability in the SGLang AI inference framework allows attackers to deliver malicious pickle payloads...
- Security
CVE-2026-46339: 9Router Unauthenticated Plugin Registration & MCP Command Execution
A critical CVSS 10 vulnerability in 9Router AI router versions 0.4.30–0.4.36 allows unauthenticated attackers to register custom plugins and execute...
- Security
CVE-2026-61736: LightRAG Critical CORS Credential Bypass (CVSS 9.3)
LightRAG's default server configuration combines CORS_ORIGINS=* with allow_credentials=True, allowing any origin to make credentialed cross-origin...
- News
Google Gemini CLI Jailbroken and Used as a Hacking Agent to Run a Malware Botnet
Trend Micro researchers discovered a Russian-speaking threat actor named 'bandcampro' who jailbroke Google's open-source Gemini CLI to operate an...
- News
We Built a Vulnerability Vending Machine: AI Tokens In, Zero-Days Out
Security firm Intruder built an AI-powered system that combines code slicing with large language models to automatically discover complex software...
- News
Weekly Recap: ShareFile Threat, Citrix Bleed 2 Ransomware, and AI Coding Attacks
This week's biggest threats: Progress Software orders ShareFile shutdown over an undisclosed zero-day-level risk, ransomware groups weaponize Citrix Bleed...
- Security
CVE-2026-60090: PraisonAI SQL Injection via Unvalidated Dimension Parameter in Vector Store Backends
A CVSS 9.8 critical SQL injection vulnerability in PraisonAI before 4.6.78 allows attackers to exploit the unvalidated dimension argument in PGVector and...
- Security
CVE-2026-61445: PraisonAI AICoder Arbitrary File Write and Command Injection via LLM Tool Calls
A CVSS 9.9 critical vulnerability in PraisonAI before 4.6.78 allows attackers to write files to arbitrary filesystem locations and execute arbitrary OS...
- Security
CVE-2026-61447: PraisonAI CodeAgent Remote Code Execution via Unsandboxed Python Execution
A CVSS 10.0 critical vulnerability in PraisonAI before 1.6.78 allows attackers to achieve remote code execution by injecting malicious prompts that...
- News
'Ghostcommit' Hides Prompt Injection in Images to Fool AI Agents and Steal Secrets
Security researchers have demonstrated 'Ghostcommit,' a technique that embeds prompt injection payloads inside PNG images to bypass AI code review tools...
- News
Lone Attacker Uses AI to Breach AWS Cloud Environment in 72 Hours
A single threat actor leveraged AI workflows, chained cloud misconfigurations, and stolen credentials to breach a large Amazon Web Services customer...
- News
AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It
Researchers at the AI Now Institute have demonstrated a 'Friendly Fire' attack that tricks AI coding agents — including Claude Code, Gemini CLI, and...
- News
What Changes When AI Writes Your Code: Supply Chain Security in the Age of LLMs
Software supply chain security was already complex. Now that AI coding assistants are writing production code, security teams face new questions about...
- News
JadePuffer: The First Fully Autonomous LLM-Driven Ransomware Attack
Security researchers at Sysdig have documented JadePuffer — an agentic threat actor powered entirely by a large language model that independently...
- News
Software Is Now Written at the Speed of Thought. Security Isn't.
AI-assisted code generation has collapsed the time between idea and deployment, but security review cycles have not kept pace. The gap between how fast...
- News
Weekly Recap: Proxy Botnets, Browser Ransomware, AI Agent Tricks, Fake PoC Malware
This week's threat roundup covers residential proxy botnets hiding in streaming boxes, browser-based ransomware campaigns, AI agent abuse techniques, and...
- News
Chinese LLMs Broaden the Gap Between Attackers & Defenders
China's GLM 5.2 finds vulnerabilities at $0.17 each and outperforms frontier Western models on security benchmarks — while AI-enabled adversary activity...
- News
Armored Likho Targets Government Agencies, Power Sector with BusySnake Stealer
Kaspersky has identified a previously undocumented APT group — Armored Likho (aka Eagle Werewolf) — deploying an AI-assisted Python infostealer called...
- News
Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution
Two critical vulnerabilities (CVE-2026-50548, CVE-2026-50549) dubbed DuneSlide allow zero-click prompt injection attacks to escape Cursor IDE's sandbox...
- News
AI Agent Exploits Langflow RCE to Automate Database Ransomware Attack
Sysdig researchers documented the first fully autonomous AI-driven ransomware campaign, where threat actor JADEPUFFER used an AI agent to chain Langflow...
- News
Anthropic's AI Finds Bugs. IBM Bets $5B It Can Fix Them.
IBM and Red Hat announced Project Lightwell — a $5 billion commitment to secure open-source supply chains using Anthropic's Mythos AI model, which found...
- News
ThreatsDay: AI Compute Hijacking, Apple Email Flaw, BlueHammer Ransomware + 14 Stories
This week's security roundup covers AI compute theft, a newly discovered Apple Mail vulnerability, the emerging BlueHammer ransomware group, and 14...
- News
Decades-Old Bash Tricks Expose AI Coding Agents to Supply Chain Attacks
Security researchers have found that classic Bash shell techniques — some dating back decades — can bypass the safeguards in most open-source AI coding...
- News
Langflow RCE Exploited to Deploy Monero Miner on Exposed AI App Endpoints
Threat actors are actively weaponizing CVE-2026-33017, a critical unauthenticated RCE flaw in Langflow, to deploy a Monero miner via the lambsys...
- Newsletter
June 30 Digest: BlueHammer Zero-Day, Ransomware Goes Corporate, AI Supply Chain Risks & Nation-State ICS Threats
A Microsoft Defender zero-day fuels ransomware before any patch exists; researchers dissect how syndicate groups run HR departments and tiered pricing;...
- News
In Other News: Chinese Mythos-Like AI, Tata Electronics Breach, Snyk Layoffs
Qihoo 360 unveils Tulongfeng — a Chinese rival to Anthropic's Mythos AI vulnerability finder; the World Leaks ransomware group dumps 630 GB from Tata...
- News
Nebulock Raises $25 Million for AI-Native Contextual Security
Boston-based Nebulock has closed a $25 million Series A led by FirstMark to expand its AI-native contextual threat hunting platform, which has performed...
- News
Cisco Adds NHI to Security Stack With Astrix, WideField Acquisitions
Cisco has acquired Astrix Security and WideField to build out non-human identity (NHI) protection capabilities, betting that securing AI agents, service...
- News
Clean GitHub Repo Tricks AI Coding Agents Into Running Malware
Researchers demonstrate how a seemingly clean, scanner-safe GitHub repository can silently execute a malicious payload when an AI coding agent clones and...
- News
More Malicious OpenClaw Skills Threaten AI Supply Chain
Unit 42 researchers identified five persistent malicious skill packages on ClawHub — OpenClaw's AI agent marketplace — including infostealers disguised as...
- News
Data Exposure Flaws in Dify AI Platform Put 1 Million+ App Tenants at Risk
Security researchers discovered multi-tenant isolation failures in the Dify AI platform that allowed attackers to read private conversations from other...
- Newsletter
June 23 Digest: FortiBleed, Klue/Salesforce Supply Chain, Squidbleed, GitHub Actions Fix
A Russian IAB harvests 110M credentials from FortiGate firewalls; the Icarus group drains hundreds of Salesforce orgs via Klue OAuth tokens; a 29-year-old...
- News
Microsoft Fixes AutoGen Studio Flaw That Enabled Code Execution
Microsoft has patched the AutoJack vulnerability chain in AutoGen Studio, its AI agent prototyping interface, which allowed attackers to manipulate agents...
- News
Researchers Detail DifyTap Flaws in Dify That Could Expose AI Chats Across Tenants
Four vulnerabilities dubbed DifyTap were disclosed in the open-source AI workflow platform Dify, enabling attackers to silently read AI conversations from...
- News
Every AI Agent Is an Identity. Most Organizations Don't Treat Them That Way
AI agents can access databases, trigger workflows, deploy code, and interact with critical business systems — often with little oversight. Token Security...
- News
AutoJack Attack Lets One Web Page Hijack AI Agent for Host Code Execution
Microsoft researchers have detailed AutoJack, a novel exploit chain that turns AI browsing agents into delivery vehicles for remote code execution by...
- News
Forget Data Leakage: Shadow AI's Real Threat Is Access Control
The original shadow AI concern — employees pasting sensitive data into public tools — has been overtaken by a more dangerous problem: unsanctioned AI apps...
- News
From Assistive to Agentic: The AI Shift That's Redefining Threat Management
Enterprise security teams are sitting on 40+ tools generating overlapping alerts, yet breach dwell times remain stubbornly high. Agentic AI is changing...
- News
Malicious JetBrains Plugins Steal AI API Keys as Chrome Extensions Capture Chatbot Chats
Researchers have uncovered a coordinated malware campaign involving 15 malicious JetBrains Marketplace plugins posing as DeepSeek-powered AI coding...
- Newsletter
June 17 Digest: Teams C2 Evasion, Copilot Data Theft, iRhythm Breach, cPanel KEV
DragonForce hides C2 inside Microsoft Teams relay traffic; a SearchLeak attack weaponizes M365 Copilot for one-click data exfiltration; iRhythm confirms...
- News
LiteLLM Vulnerability Chain Lets Low-Privilege Users Take Over AI Gateway Servers
Researchers at Obsidian Security disclosed a chain of three vulnerabilities in the widely deployed LiteLLM open-source AI gateway that allows a default...
- News
SearchLeak: New Attack Turned Microsoft 365 Copilot into 1-Click Data Theft Tool
Researchers disclosed SearchLeak, a critical vulnerability chain in Microsoft 365 Copilot Enterprise that allows attackers to steal sensitive data from a...
- News
ThreatsDay Bulletin: Worm Code Leaked, AI Agent Phished, Claude Code Patch + 28 New Stories
This week's threat intelligence roundup covers a supply chain attack kit posted publicly, a $5,000-per-month RAT that clones browser sessions, AI agents...
- News
Aryon Security Raises $29 Million in Series A Funding
In the post-Mythos era, Aryon Security's platform helps organizations enforce security controls across multi-cloud environments as AI-generated...
- News
Path Traversal Flaw in AI Dev Platform Langflow Exploited in Attacks
Attackers are actively exploiting CVE-2026-5027, a high-severity path traversal vulnerability in Langflow, to write arbitrary files on exposed servers....
- News
Unpatched Langflow Flaw CVE-2026-5027 Exploited for Unauthenticated RCE
A high-severity path traversal flaw (CVE-2026-5027, CVSS 8.8) in the AI application builder Langflow is being actively exploited with no patch available....
- News
AI Agent Uncovers 21 Zero-Days in FFmpeg; Chrome Patches Record 429 Bugs
An autonomous AI security agent found 21 previously unknown vulnerabilities in FFmpeg, the media library powering countless applications. The same week…
- News
New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration
OpenAI has begun rolling out a new Lockdown Mode to ChatGPT for eligible personal accounts, restricting tool capabilities that could be exploited in prompt…
- News
Adaptive, Agentic AI Worms Loom as the Next Major Enterprise Threat
Security researchers warn that adaptive agentic AI worms — described as 'viruses with wings and brains' — will likely strike enterprise environments within a…
- News
In Other News: Anthropic Maps AI Threats, Unpatched Comodo Flaw, Palantir Chief Eyed for CISA
This week's cybersecurity roundup covers Anthropic's new AI threat taxonomy, an unpatched Comodo security flaw, Palantir's Alex Karp reportedly under…
- News
Only 10% of SOCs Say They're Getting Excellent Value From AI — What the Second Wave Must Deliver
A new survey reveals only 10% of Security Operations Centers report getting excellent value from AI investments. As billions flow into AI-powered security…
- News
Security of 100 AI Agents Tested and Ranked – What You Need to Know
A new AI Risk Quadrant framework has benchmarked 100 AI agents across three dimensions: vulnerability to compromise, potential breach impact, and strength of…
- News
Autonomous AI Tool Finds 2-Year-Old RCE Flaw in Redis (CVE-2026-23479)
Redis has patched a use-after-free vulnerability in its blocking-client code that allows authenticated users to execute arbitrary OS commands on the database…
- Security
CVE-2026-4035: MLflow AI Gateway Credential Exfiltration via Env Variable Resolution
A CVSS 9.1 critical flaw in MLflow AI Gateway allows server-side environment variables in api_key fields to be resolved and exfiltrated to attacker-controlled…
- News
Beyond Assume-Breach: How AI-Native Security Will Reshape Enterprise Defense
Twenty years after Dark Reading launched, security leaders are looking beyond the assume-breach paradigm toward AI-native, hyper-segmented enterprise defense…
- News
OpenAI Codex Authentication Tokens Stolen via codexui-android npm Supply Chain Attack
Cybersecurity researchers have uncovered a malicious npm package named codexui-android that targets developers using OpenAI Codex by masquerading as a…
- News
As Global Powers Explore Humanoid Robots, Cyber-Risk Looms
Nation-states are racing to dominate the embodied AI and humanoid robotics market, but as governments and militaries integrate these systems, the…
- News
Frontier AI Reinforces the Future of Modern Cyber Defense
As OpenAI and Anthropic push frontier AI capabilities forward, SentinelOne argues that AI-native, machine-speed cyber defense is now essential — and that the…
- News
GCHQ Chief: AI Is an 'Unstoppable Force' with Offensive and Defensive Cyber Ramifications
Anne Keast-Butler, head of the UK's GCHQ signals intelligence agency, has warned that artificial intelligence represents an unstoppable force in cyberspace…
- News
Geordie Raises $30 Million for AI Security and Governance Platform
AI security startup Geordie closes a $30M round led by Balderton Capital to help enterprises detect and govern AI risk across their environments.
- News
Cybersecurity Evolution: From Perimeter Defense to AI-Native Security
On Dark Reading's 20-year mark, a tech lens on how cybersecurity moved from castle-and-moat perimeters to AI-native, identity-first cloud defense.
- News
UK Cyberspying Chief Calls AI 'an Unstoppable Force' and Warns About Russia
UK signals-intel chief warns AI is reshaping threats as an unstoppable force while Russia escalates hostile gray-zone activity below open conflict.
- News
Open Source DockSec Uses AI to Cut Through Vulnerability
DockSec, an OWASP incubator project, combines multiple container security scanners with AI-generated plain-English remediation guidance and exact Dockerfile.
- News
Claude Mythos AI Finds 10,000 High-Severity Flaws in Widely
Anthropic has disclosed that Project Glasswing — its AI-powered vulnerability research initiative using the Claude Mythos system — has uncovered more than...
- Security
CVE-2026-2611: MLflow 3.9.0 Improper Origin Validation
A critical CVSS 9.6 vulnerability in MLflow 3.9.0 allows a remote attacker to exploit improper origin validation in the MLflow Assistant's /ajax-api...
- News
5 Steps to Managing Shadow AI Tools Without Slowing Down
80% of employees currently use unapproved AI tools at work, yet only 12% of companies have formal AI governance policies. Adaptive Security outlines a...
- News
In Other News: Big Tech vs Canada Encryption Bill, Cisco's
Other noteworthy stories this week: Big Tech firms push back against Canada's encryption legislation, Cisco releases a free AI security specification, and...
- News
The Boring Stuff Is Dangerous Now
AI agents capable of discovering and exploiting obscure vulnerabilities are emerging alongside developers producing vast amounts of potentially flawed...
- News
OpenAI Asks macOS Users to Update After TanStack npm Supply
OpenAI is urging macOS users to update their software following an expanding supply chain attack that compromised TanStack and additional npm and PyPI...
- News
PraisonAI CVE-2026-44338 Auth Bypass Targeted Within Hours
Threat actors began exploiting CVE-2026-44338, a missing authentication flaw in the PraisonAI multi-agent orchestration framework, within just four hours...
- News
ThreatsDay Bulletin: PAN-OS RCE, Mythos cURL Bug, AI
This week's threat roundup covers an actively exploited PAN-OS RCE granting root access, Anthropic's Mythos AI finding a cURL memory safety bug, AI...
- News
Weaponized AI: The New Frontier of Fraud and Identity
Fake identity fraud powered by generative AI is projected to cause $40 billion in losses annually. Security leaders are warned that static defenses are no...
- News
Ollama Out-of-Bounds Read Flaw Allows Remote Process Memory
Researchers have disclosed a critical out-of-bounds read vulnerability in Ollama that enables remote unauthenticated attackers to leak the entire process...
- News
Cisco Releases Open Source Tool for AI Model Provenance
Cisco has released a new open source toolkit designed to track and verify the provenance of AI models throughout the supply chain, addressing risks from...
- News
AI Finds 38 Security Flaws in Electronic Health Record
Security researchers using AI-assisted analysis discovered 38 vulnerabilities in OpenEMR, an open-source electronic health record platform used by more...
- News
Critical Gemini CLI Flaw Enabled Host Code Execution
A critical vulnerability in Google's Gemini CLI allowed an attacker to plant a malicious configuration file that executed commands outside the sandbox,...
- News
Critical Unpatched Flaw Leaves Hugging Face LeRobot Open to Unauthenticated RCE
Cybersecurity researchers have disclosed CVE-2026-25874, a critical unauthenticated remote code execution vulnerability (CVSS 9.3) in Hugging Face's...
- News
Hackers Are Exploiting a Critical LiteLLM Pre-Auth SQLi Flaw
Threat actors are actively exploiting CVE-2026-42208, a critical pre-authentication SQL injection vulnerability in the LiteLLM open-source LLM gateway,...
- Newsletter
Apr 28 Digest: Medtronic 9M Breach, GitHub RCE, LiteLLM
ShinyHunters hits Medtronic and ADT in the same week, exposing millions of records; a critical one-push RCE lands in GitHub; LiteLLM's pre-auth SQL...
- News
Hypersonic Supply Chain Attacks: One Solution That Didn't
SentinelOne details how its AI-driven behavioral detection stopped three zero-day supply chain attacks at machine speed — without prior knowledge of the...
- News
LMDeploy CVE-2026-33626 Flaw Exploited Within 13 Hours of Disclosure
A high-severity SSRF vulnerability in LMDeploy, a widely used open-source LLM deployment toolkit, was actively exploited in the wild less than 13 hours...
- Security
CVE-2026-26210: KTransformers Unsafe Deserialization RCE
KTransformers through version 0.5.3 contains a critical unsafe deserialization vulnerability in its balance_serve backend mode, where an unauthenticated...
- News
Cloud Platform Vercel Says Company Breached Through
Vercel has confirmed a security breach in which limited customer credentials were exposed after an employee's workstation was compromised through malware...
- Newsletter
Apr 21 Digest: Vercel AI Tool Breach, DPRK $290M, ActiveMQ
Vercel confirms breach through a compromised third-party AI coding tool; North Korean hackers attributed to a $290 million crypto theft; 6,400 Apache...
- News
Anthropic MCP Design Vulnerability Enables RCE, Threatening
Cybersecurity researchers have discovered a critical by-design weakness in the Model Context Protocol architecture that enables arbitrary command...
- News
SGLang CVE-2026-5760 (CVSS 9.8) Enables RCE via Malicious
A critical CVSS 9.8 command injection vulnerability in the SGLang AI inference framework allows attackers to achieve remote code execution by supplying a...
- News
Vercel Breach Tied to Context AI Hack Exposes Limited
Vercel's security breach originated from the compromise of Context.ai, a third-party AI tool used by a company employee, allowing attackers to gain...
- News
Vercel Employee's AI Tool Access Led to Data Breach
Stolen OAuth tokens from a compromised employee AI tool enabled attackers to pivot into Vercel's internal systems. Security researchers warn that...
- News
Why the Axios Attack Proves AI Is Mandatory for Supply
The North Korean supply chain attack on Axios — a JavaScript library with 100 million weekly downloads — highlights why human-scale monitoring can no...
- News
Analysis of 216M Security Findings Shows a 4x Increase in Critical Risk (2026 Report)
OX Security analyzed 216 million security findings across 250 organizations over 90 days and found critical risk grew by nearly 400% year-over-year, even...
- News
Microsoft, Salesforce Patch AI Agent Data Leak Flaws
Prompt injection vulnerabilities in Salesforce Agentforce and Microsoft Copilot would have allowed unauthenticated attackers to exfiltrate sensitive CRM...
- News
Can Anthropic Keep Its Exploit-Writing AI Out of the Wrong
Anthropic's Claude Mythos Preview model can autonomously find and exploit zero-days across every major OS and browser at a 72.4% success rate — and it's...
- Security
CVE-2026-39888: PraisonAI Sandbox Escape Enables Remote
A critical sandbox escape vulnerability in PraisonAI's multi-agent framework allows attackers to bypass the Python code execution sandbox, defeating the...
- Security
CVE-2026-39890: PraisonAI YAML Injection Achieves Remote
A critical code injection vulnerability in PraisonAI's AgentService allows attackers to craft malicious YAML files using dangerous js-yaml tags such as...
- News
Anthropic's Claude Mythos Finds Thousands of Zero-Day Flaws
Anthropic's new Project Glasswing initiative uses a preview of its frontier model Claude Mythos to autonomously discover thousands of previously unknown...
- Security
CVE-2026-1114: lollms JWT Weak Secret Key Allows Admin
A critical vulnerability (CVSS 9.8) in parisneo/lollms v2.1.0 allows attackers to brute-force the application's JWT secret key offline, forge...
- News
How LiteLLM Turned Developer Machines Into Credential
The TeamPCP threat actor's March 2026 supply chain attack against LiteLLM exposed a dangerous blind spot: developer workstations running local AI agents...
- News
Critical Vulnerability in Claude Code Emerges Days After
Adversa AI has discovered a critical vulnerability in Anthropic's Claude Code AI coding assistant, disclosed just days after Anthropic accidentally leaked...
- News
Mercor Confirms Security Incident Tied to LiteLLM Supply
AI hiring platform Mercor has confirmed a security incident linked to the LiteLLM PyPI supply chain attack carried out by TeamPCP. Separately, Lapsus$...
- News
Claude Code Source Leaked via npm Packaging Error
Anthropic confirmed that internal source code for its Claude Code AI coding assistant was accidentally published to npm due to a human packaging error. No...
- News
Claude Code Source Code Accidentally Leaked in NPM Package
Anthropic accidentally published the source code for Claude Code — its normally closed-source AI coding assistant — inside an npm package. The company...
- News
CISA: New Langflow Flaw Actively Exploited to Hijack AI
CISA has added CVE-2026-33017, a critical unauthenticated remote code execution vulnerability in the Langflow AI framework, to its Known Exploited...
- News
Paid AI Accounts Are Now a Hot Underground Commodity
New research from Flare Systems reveals that premium AI platform access — including ChatGPT Plus, Claude Pro, and raw API keys — has been systematically...
- News
Supply Chain Attack Hits Widely-Used AI Package, Risking
Malicious versions of LiteLLM — a Python package with 3 million daily downloads present in roughly 36% of cloud environments — were quietly pushed to PyPI...
- News
AI Flaws in Amazon Bedrock, LangSmith, and SGLang Enable
Security researchers disclosed critical flaws across three major AI platforms: Amazon Bedrock AgentCore's sandbox can be bypassed via DNS to exfiltrate...
- Newsletter
Mar 17 Digest: GlassWorm Poisons Python, n8n RCE Hits KEV
This week: GlassWorm escalates with 72 malicious Open VSX extensions and a GitHub token force-push campaign poisoning hundreds of Python repos; CISA adds...
- News
Shadow AI Is Everywhere. Here's How to Find and Secure It.
Shadow AI is quietly spreading across SaaS environments as employees adopt new AI tools without IT oversight. Security teams can discover AI apps, monitor...
- News
Weekly Recap: Chrome 0-Days, Router Botnets, AWS Breach
This week's cybersecurity roundup covers the actively exploited Chrome zero-day CVE-2026-2441, the Aisuru router botnet record DDoS attack, a supply chain...
- News
OpenClaw AI Agent Flaws Enable Prompt Injection, 1-Click
China's CNCERT has warned that OpenClaw (formerly Clawdbot/Moltbot), the viral self-hosted AI agent, carries over 250 disclosed vulnerabilities including...
- Project
Securing AI-Assisted Development with Claude Code
Build guardrails around AI-generated code with Claude Code hooks, security-scanning agents, OWASP-aware prompting, and automated secret detection. A...
- News
Cline CLI Supply Chain Attack Installs Unauthorized
A compromised npm publish token was used to inject a malicious postinstall script into Cline CLI version 2.3.0 on February 17, 2026, silently installing...
- Newsletter
Late February Roundup: New Guides, Checklists & Threat
New IT offboarding checklist, endpoint security baseline, BGP monitoring guide, ClickFix detection guide, plus AI-powered attacks on FortiGate devices, a...
- News
WormGPT Hacked: 19,000 Cybercriminal AI Platform Users
A threat actor has published a database allegedly containing 19,000 user records from WormGPT, the underground AI platform marketed for offensive hacking...
- Security
Critical RCE in Microsoft Semantic Kernel Python SDK
A maximum-severity code injection vulnerability in Microsoft's Semantic Kernel Python SDK allows authenticated attackers to execute arbitrary code through...
- News
AI-Driven Threats Accelerate: Agentic Attacks, Model
Multiple industry reports warn that 2026 marks the emergence of agentic AI threats — autonomous systems capable of planning and executing multi-step...
- News
Microsoft Discovers 'AI Recommendation Poisoning' via Chatbot Prompts
Microsoft's Defender team tracked over 50 unique prompt injection payloads from 31 companies using 'Summarize with AI' buttons to manipulate chatbot...