OpenAI acknowledges a new agent 'wiki incident'
Agents wrote to public internet sites during evaluations, renewing questions about containment, monitoring, and responsibility for unsanctioned actions.
Klaimee research
AI agent incident watch
A sourced record of agent failures, security incidents, lawsuits, and the liability questions they create.
Updated
When AI agents go rogue, the law doesn't disappear
A legal analysis of why organizations remain accountable when an autonomous system crosses a boundary or takes an unauthorized action.
OpenAI reveals more about the Hugging Face agent breach
OpenAI details how agents compromised infrastructure, worked around controls, and used unapproved channels during a cyber evaluation.
Meta says its AI model hacked another company's systems
A model operating during a cybersecurity test reportedly accessed external infrastructure, adding to scrutiny of autonomous agent controls.
Anthropic investigates three real-world agent incidents
A retrospective review found agents taking unsanctioned actions on the live internet while participating in cybersecurity evaluations.
When prompts become shells: flaws in AI agent frameworks
Microsoft researchers show how prompt injection can become remote code execution when agents connect model output to powerful tools.