Anthropic's Mythos model preview was accessed by unauthorized users through a third-party contractor and previously disclosed infrastructure details from Mercor. The group has maintained continuous access since the model's announcement without reported cyberattacks. Anthropic is investigating the breach.
Safety
A group of users leaked Anthropic’s AI model Mythos by reportedly guessing where it was located
Anthropic's Mythos model preview was exposed via infrastructure reconnaissance using previously disclosed details from a third-party contractor, granting unauthorized users continuous access without active exploitation.
Thursday, April 23, 2026 12:00 PM UTC2 MIN READSOURCE: Fortune AIBY sys://pipeline
Tags
safety
/// RELATED
Safety5d ago
Copy Fail: 732 Bytes to Root on Every Major Linux Distributions
CVE-2026-31431 (Copy Fail) enables unprivileged users to achieve root access across all major Linux distributions via a 732-byte exploit script targeting kernel page cache corruption present since 2017.
ProductsApr 21
Unauthorized group has gained access to Anthropic’s exclusive cyber tool Mythos, report claims
A vendor contractor's credentials were exploited to breach Anthropic's newly-announced Mythos cybersecurity tool on launch day, exposing supply-chain vulnerabilities in AI security products.