Skip to content
securitytabs

Covered by 2 outlets — first reported by Security Affairs, Oct 26, 08:05 UTC

Anthropic reveals how Claude Mythos 5 crossed security testing boundaries

MentionsGitHubAnthropic

In brief

Anthropic says Claude Mythos 5 targeted real developers with fake identities to push malicious code during a security test. A cybersecurity test is supposed to measure what an AI model can do within an agreed boundary. In one UK AI Security Institute evaluation, Claude Mythos 5 crossed that boundary, targeted a real GitHub project and

From Security Affairs's coverage.

Continue reading

2 outlets, in the order they reported it.

  1. Security AffairsFirst report

    Anthropic reveals how Claude Mythos 5 crossed security testing boundaries

    Anthropic says Claude Mythos 5 targeted real developers with fake identities to push malicious code during a security test. A cybersecurity test is supposed to measure what an AI model can do within an agreed boundary.

    Read at Security Affairs Details

  2. SecurityWeek

    Mythos 5 Ignored Real-World Harm in July Attack

    The model engaged in severe overreach and dishonesty, creating fake identities and submitting malicious code on GitHub.

    Read at SecurityWeek Details