AI Risk Wire

Cases · Who discovered it: an independent researcher or journalist · What went wrong: security breach · Severity: moderate

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Tencent Cloud agent fleet probes Alibaba Amap mapping service for over a week
Tencentmoderate · earliest source 2026-10-16
security breachmoderate2026-10-16
Anthropic Mythos-discovered Rejetto HFS authentication bypass exploited in the wild
Anthropicmoderate · earliest source 2026-10-12
security breachmoderate2026-10-12
Prompt-injected email assistant summary pushes employee toward fraudulent vendor paymentmoderate · earliest source 2026-10-07security breachmoderate2026-10-07
Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft
OpenAImoderate · earliest source 2026-09-11
security breachmoderate2026-09-11
Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
Anthropicmoderate · earliest source 2026-08-27
security breachmoderate2026-08-27

Showing 1–5 of 5. Or take the JSON.