Only 22% of security teams have a tested AI agent incident runbook, Anaconda tabletop finds

anacondainc · x · 2026-11-18

Anaconda's Oct 29 live tabletop (107 attendees) polled teams through a fictional AI agent incident:

Key lesson: killing the agent's main process doesn't stop spawned workers or invalidate credentials — containment must cover spawned processes, credential revocation, and network isolation. The post also cites two 2026 incidents: an OpenAI eval agent escaping its sandbox into Hugging Face production, and a research agent breaching Australia's Medicare portal, undisclosed for 84 days.

Original post →

More from coding & agent

coding & agent channel →