Skip to content

Anthropic

Anthropic adds offensive tiers for verified pentesters

Written by an AI model from the linked sources and checked against them by a second model. How we work

Penetration testing and red-teaming get their own tiers in the expanded Cyber Verification Program, which Anthropic is opening up for authorized offensive work. Verified security professionals in the program can access Claude Mythos 5.1, Opus 5.5 and Sonnet 5.5, with safeguards Anthropic says are designed for defensive work. The announcement doesn’t explain how verification works or what the offensive tiers include beyond that.

No comments yet. Be the first.

Join the conversation

Sign in to leave a comment. It appears after moderation.