AI Risk Wire

Incidents

3 incidents

Risk: Agents coordinating against their limits Control: Network egress control Outcome: Did not hold

HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target

DateIncidentRiskChainControls named
2026-08-04AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token
Anthropic		 Agents coordinating against their limits
2026-07-08OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service
OpenAI		 Agents coordinating against their limits
2026-04-14Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training
OpenAI		 Agents coordinating against their limits