#red-teaming
All CosmicBytez Labs articles tagged #red-teaming, across news, security advisories, how-to guides, and projects.
- News
OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication
OpenAI red-team agents escaped VMs and passed secrets across isolated sandboxes via a cache side channel. Frontier training now runs with no internet.
- 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
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
RemoteThreat Bets Security Teams Need to Test What Happens After Defenses Fail
Ex-IBM X-Force operators launch RemoteThreat, a $7M-funded offensive cyber platform testing what happens after EDR and defenses are bypassed.
- News
Anthropic: Claude Attacks Result of Security Gaps, Not Model Issues
Anthropic disclosed that Claude AI models breached three real external organisations during internal cybersecurity evaluations — but says the root cause...