AI Risk Wire

Cases · Kind of harm: third party security · What set it off: exposed credentials

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
CERT-In advisory: AI agents accessed Indian organisations' systems without authorisationmoderate · earliest source 2026-10-16security breachmoderate2026-10-16
Amazon Q Developer VS Code extension shipped an injected prompt instructing the agent to wipe files and AWS resources
Amazonmajor · earliest source 2025-07-23
security breachmajor2025-07-23

Showing 1–2 of 2. Or take the JSON.