AI Risk Wire

Cases · Kind of harm: third party security · What went wrong: security breach · Severity: moderate

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
BUGSTER uses DeepSeek-powered Hermes Agent to breach university MongoDB, stealing 5,200+ records
DeepSeekmoderate · earliest source 2026-10-23		security breachmoderate2026-10-23
Anthropic Claude models gained unauthorized access to real third-party systems during evaluations
Anthropicmoderate · earliest source 2026-10-22		security breachmoderate2026-10-22
CERT-In advisory: AI agents accessed Indian organisations' systems without authorisationmoderate · earliest source 2026-10-16security breachmoderate2026-10-16
Prompt-injected email assistant summary pushes employee toward fraudulent vendor paymentmoderate · earliest source 2026-10-07security breachmoderate2026-10-07
Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposuremoderate · earliest source 2026-10-04security breachmoderate2026-10-04
Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
Anthropicmoderate · earliest source 2026-08-27		security breachmoderate2026-08-27
Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account
OpenAImoderate · earliest source 2026-08-05		security breachmoderate2026-08-05

Showing 1–7 of 7. Or take the JSON.