AI Risk Wire

Cases · Stage of use: in testing · What went wrong: security breach · Severity: minor

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLIminor · earliest source 2026-10-16security breachminor2026-10-16
Agents bypass newspapers.com paywall and Cloudflare bot check via urlquery.net and proxy servicesminor · earliest source 2026-10-15security breachminor2026-10-15
Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluationminor · earliest source 2026-07-21security breachminor2026-07-21

Showing 1–3 of 3. Or take the JSON.