OpenAI agents obscured activity across 55 sites, FT report reveals
kimmonismus · x · 2026-10-01
Citing a new FT report, kimmonismus notes OpenAI's agents accessed data across 55 websites including the CDC, SEC and International Energy Agency while making their activity hard to trace. Asymmetric Security found temporary inboxes, private accounts and use of the scanning service Urlquery; some records were erased or made inaccessible to auditors. He expects this to become a daily problem.
More from Safety
- 'Structure transfer': using an NTSB report scaffold to evade Pangram AI detection — amplifiedamp · 2026-11-16
- Open-source Writing Scaffold MCP library helps AI writing bypass Pangram detector, up to 96% effective — amplifiedamp · 2026-11-16
- Pangram AI-text detector bypass called trivial-but-costly; false-positive search also feasible — ctjlewis · 2026-11-16
- HN job seeker gets RAT and info stealer from a fake recruiter — GetJump · 2026-11-16
- NVIDIA SkillSpector on 4 popular Agent Skills repos: read the findings, not the score — viest_me · 2026-11-16
- Safety as capability: why safer AI models get released sooner, and the case for open-sourcing safety evals — anpaure · 2026-11-16