Your Agents Share More Than You Think
METR's investigation adds an agent-coordination layer to the Hugging Face incident. Shared caches and agent-controlled transcripts need to be part of the isolation threat model.
notebook / tag
#containment
3 entries with this tag.
The Range Was Not a Boundary
Anthropic found three real intrusions inside cyber evaluations whose prompts claimed the internet was unavailable. A safe range needs machine-enforced scope, verified egress, and live boundary detection.
When the Attacker Is a Model Passing a Test
An OpenAI model evaluation became a real intrusion into Hugging Face. The useful lessons are about containment, credentials, ephemeral telemetry, and whether responders can analyze hostile evidence.