[metr]

October 23, 2026

• METR and Redwood red-teamed OpenAI's internal misalignment monitoring with codebase-level access. Over three weeks (July 21–August 11) they found a way agents could in principle bypass Codex sandboxing and Auto-Review, an exploit that could hide hundreds of recent actions from monitors, and blind spots around context compaction and client-controlled headers. They estimated 75–94% of agentic internal Responses API traffic from models at least as strong as GPT-5.5 was eligible for monitoring, and 99.2% of the internal Codex agent subset. OpenAI says all vulnerabilities affecting production safeguards are patched; METR has not verified that. METR · AI & Model Security

in Two Unpatched KSMBD RCEs Go Public — and an AI Scanner Found Them

October 1, 2026

• The FTC has opened a consumer-protection investigation into OpenAI, Anthropic and other leading AI labs, with Civil Investigative Demands for documents and executive testimony expected within weeks; safety org METR is also in scope. The probe predates the Hugging Face agent incident (Reuters, The Decoder). (discussion) · Industry & Policy

in An Encoded Character Away From Admin: Cisco SD-WAN Manager Exploited in the Wild

September 2, 2026

• Attackers stole a METR API key and burned roughly $600,000 in AI model credits before anyone noticed — for weeks. The nonprofit that evaluates frontier models for long-horizon agentic capability disclosed two separate intrusion attempts (The Register, Dark Reading). Credential hygiene and spend alerting on model APIs is now a real attack surface, not a billing concern (earlier coverage). · AI & Model Security

in OpenAI Says Astra Crossed the Line: Autonomous Zero-Day Discovery at "Critical" Cyber Risk