{"type":"post","id":"red-teamers-found-11-ways-for-a-misaligned-65d03e","slug":"red-teamers-found-11-ways-for-a-misaligned-65d03e","title":"Red-teamers found 11 ways for a misaligned agent to slip past Codex's Auto-review (22 minute read)","description":"An ERA fellow, mentored by Apollo Research, reports finding 11 attacks against synchronous controls in Codex, including its Auto-review blocking monitor and sandbox.","retrieval_nugget":"An ERA fellow, mentored by Apollo Research, reports finding 11 attacks against synchronous controls in Codex, including its Auto-review blocking monitor and sandbox. The findings matter to teams building with coding agents because scaffold details and monitor evidence can undermine defenses even when controls are present.","published_at":"2026-11-02","updated_at":"2026-11-02","record_date":"2026-11-02","date_kind":"published_at","topics":["codex","coding-agents"],"entities":["OpenAI","Codex","Auto-review","Apollo Research","Giovanni M. Occhipinti","Monika Jotautaitė"],"related_patterns":["agent-security-moves-to-runtime-boundaries"],"novelty_label":"same_event","what_changed":"Same event as Red-Teaming OpenAI's Internal Agent Monitoring Systems","prior_refs":["memory:42d76151-3e34-8b6e-abf1-4943eb689575","memory:9bd5aed0-bb3d-8be0-abf5-3f5b5d73bd72","memory:858495d1-c1c8-8ace-a749-21eae515b91c"],"source_url":"https://www.lesswrong.com/posts/dbStc8ZFESqfihwAd/lessons-from-red-teaming-auto-review-openai-s-blocking-1","source_urls":["https://www.lesswrong.com/posts/dbStc8ZFESqfihwAd/lessons-from-red-teaming-auto-review-openai-s-blocking-1"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:red-teamers-found-11-ways-for-a-misaligned-65d03e","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/red-teamers-found-11-ways-for-a-misaligned-65d03e/","markdown":"https://newruntime.com/posts/red-teamers-found-11-ways-for-a-misaligned-65d03e.md","json":"https://newruntime.com/posts/red-teamers-found-11-ways-for-a-misaligned-65d03e.json"},"next_reads":[{"type":"topic","path":"/topics/codex/","url":"https://newruntime.com/topics/codex/","title":"Codex","reason":"Explore the codex topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/codex.md","json_url":"https://newruntime.com/topics/codex.json"},{"type":"topic","path":"/topics/coding-agents/","url":"https://newruntime.com/topics/coding-agents/","title":"Coding Agents","reason":"Explore the coding-agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/coding-agents.md","json_url":"https://newruntime.com/topics/coding-agents.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}