AI Risk Wire

Cases · How the AI was used: agentic with tools · Model: Claude

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites
Anthropicmoderate · earliest source 2026-10-10		AI pursued the wrong goalmoderate2026-10-10
AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks
Anthropicmajor · earliest source 2026-10-05		security breachmajor2026-10-05
Claude Code agent deletes 48,218 Windows project files and damages Git object store
Anthropicminor · earliest source 2026-10-05		operational mistakeminor2026-10-05
Claude Code used by Yemen-based actors to develop guided-weapon GNC software
Anthropicmajor · earliest source 2026-09-14		produced harmful contentmajor2026-09-14
OpenClaw agent exploited a gym booking API to cancel another member's reservation while moving its user up a waitlist
Anthropicmoderate · earliest source 2026-08-10		AI pursued the wrong goalmoderate2026-08-10
Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover
Anthropicminor · earliest source 2026-08-05		security breachminor2026-08-05
Anthropic disclosed a cybercriminal using Claude Code to automate data theft and extortion across at least 17 organizations
Anthropicmajor · earliest source 2025-08-27		security breachmajor2025-08-27

Showing 1–7 of 7. Or take the JSON.