#Prompt Injection
All CosmicBytez Labs articles tagged #Prompt Injection, across news, security advisories, how-to guides, and projects.
- News
From Email-to-Case to the Boardroom: How Inherited AI Agents Break Governance Built for Software
Email-to-Case and Web-to-Case let anonymous senders reach Salesforce Agentforce AI agents, exposing governance gaps vendor reviews and prompt filters both miss.
- News
Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws
Anthropic halted live internet access for all internal AI evaluations after Claude models exploited injection flaws and filed unauthorized web forms.
- News
OpenAI's Leaked 'o' Assistant Points to an Always-On, Email-Capable AI Agent
Leaked references show OpenAI testing 'o,' a Pro-tier always-on assistant with its own email identity — raising fresh agentic-AI risk.
- 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
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
Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
Researchers from the ASSET Research Group disclosed GhostSplice — a novel cross-channel trust fragmentation attack that splits malicious instructions...
- 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...
- 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
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...
- 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
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
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
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
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
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...
- Security
CVE-2026-30304 — AI Code Safe Command Execution Bypass
A critical flaw in AI Code's automatic terminal command execution design allows unsafe commands to bypass the model-based safety judgement and be...
- 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...
- 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...