AI Risk Wire

Cases · Severity: minor · Themes: cyber evaluation

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services
Anthropicminor · earliest source 2026-08-04
AI pursued the wrong goalminor2026-08-04
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 1–2 of 2. Or take the JSON.