AI Risk Wire

Cases · Stage of use: in testing · Model: Claude Mythos 5 · 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

Showing 1–1 of 1. Or take the JSON.