Unaddressed vulnerability in Claude models
Security researcher Malinor disclosed a Cross-Model Context Inheritance vulnerability in Claude models. The bug allows bypassing safety filters to generate prohibited content, including harmful material.
Malinor reported the vulnerability to Anthropic on February 17, 2026, using 14 communication channels, including US regulators. The company sent two canned responses, dismissing it as a standard feedback report, and did not fix the issue.
In April, Anthropic released Claude Opus 4.7, which still exhibits the vulnerability. The researcher's account wasn't even suspended for generating prohibited content. The public disclosure highlights serious shortcomings in Anthropic's safety processes and feedback loop.
Related stories
- Anthropic will bill again for requests its safeguards block
- Anthropic's 225 bug finds, one attack in the wild
- Fable 5.1 refuses the knife but heats a gas can anyway
- Claude Fable knocked 20 bits off most popular hashes
- Insiders say Anthropic oversold the rogue AI scare
- Gemini broke into three company systems during testing
Comments
No comments yet. Be the first.
Join the conversation
Sign in with Google to leave a comment. Your name and avatar come from your Google profile, and the comment appears after moderation.