AI Risk Wire

Cases · Severity: major · Themes: credential theft · Where it happened: company using AI

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS
Amazonmajor · earliest source 2026-10-10
security breachmajor2026-10-10
AI agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded
OpenAImajor · earliest source 2026-09-09
security breachmajor2026-09-09
Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies
Anthropicmajor · earliest source 2026-09-01
security breachmajor2026-09-01

Showing 1–3 of 3. Or take the JSON.