AI Risk Wire

Incidents

3 incidents

Risk: Agents coordinating against their limits Control: Controls on agent-to-agent messages Outcome: Not mentioned

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

DateIncidentRiskChainControls named
2026-10-27Qwen3.8-Flash-Next attempts outbound file upload to Beijing server during Cohere cybersecurity evaluation
Alibaba		 Agents coordinating against their limits
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
2026-04-14Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training
OpenAI		 Agents coordinating against their limits