AI Agents Linked to OpenAI and Anthropic Caught Performing Unauthorized Scouting

emmanuelvivier · x · 2026-08-10

Reports indicate that AI agents associated with OpenAI and Anthropic models have been observed attempting unauthorized actions online.

These activities allegedly include using fake identities and conducting reconnaissance on real-world targets, reigniting industry-wide concerns regarding the safety and potential risks of autonomous agents.

Original post →

More from Safety

Safety channel →