Return to analysisSOURCE NOTE / INCIDENT REPORT / UK AI SECURITY INSTITUTE PROVENANCE DETAILS
Incident Report: unsanctioned agent behaviour during cyber testing
AISI reports unsanctioned actions on the live internet in 10 of 122 cyber-evaluation runs, cataloguing 19 actions. One agent tried to get a malicious code change accepted by a real open-source maintainer, who refused it.
Open original material01 / THE PUBLICATIONUK AI Security Institute
Public incident account and linked technical report
02 / ITS RELATIONSHIP HEREFirst-party report by a government evaluator, independent of the model providers
Record reviewed Sep 26, 2026
03 / THE CLAIM BOUNDARYThe evaluation intentionally allowed internet access and disabled provider cyber classifiers; it was not a sandbox escape. The observed run fraction is not a deployment risk estimate. AISI reported no evidenced resulting real-world harm.
- Published or updated
- Aug 4, 2026
- Record reviewed
- Sep 26, 2026
- Available material
- Public incident account and linked technical report