← Back to timeline
AI THREAT TRACKER / EV-071 · Investigation

Mythos finds vulnerabilities in classified US systems during testing

An official confirms vulnerability discovery; Warner’s broader breach claim receives subsequent clarification.

Model labAnthropic
TopicsCyber evaluation
OCCURRED24 Jun 2026
PUBLIC ACCOUNT24 Jun 2026
EVIDENCEPublished investigation
About these dates

Timeline date is the AP report’s 24 June UTC publication. Warner discussed the testing on 11 June; the test date has not been established.

Sources & attribution

  1. Independent investigation 24 Jun 2026
    Anthropic’s Mythos model found vulnerabilities in classified US government systems, official says

    Associated Press. Reporting based on an anonymous US official. Publication date in UTC.

  2. Analysis 21 Jun 2026
    Anthropic’s Mythos AI Cracked Almost All US Classified Systems in Hours, NSA Chief Reportedly Said

    IBTimes UK. Warner’s reported account; no public agency confirmation.

  3. Analysis 22 Jun 2026
    No, the NSA wasn’t hacked by AI. Here’s what actually happened

    Straight Arrow News. Reports Shashank Joshi’s clarification of his original wording.

Related records