AI Risk Wire

Cases · Severity: moderate · Themes: agentic browser

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
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 1–1 of 1. Or take the JSON.