Florian Roth flags a critical Claude Code issue where deny rules can be silently bypassed because security checks cost too many tokens.
Critical Vulnerability in Claude Code Emerges Days After Source Leak
Adversa uncovers a critical flaw in Anthropic’s Claude Code. By bypassing the 50-subcommand limit, hackers can execute malignant directives in AI pipelines.
It’s a high-interest issue related to the Claude Code CLI.
You may be interested in reviewing the report I submitted to disclosure@anthropic.com.
By bypassing the 50-subcommand limit, hackers can execute malignant directives in AI pipelines.
Critical Claude Code vulnerability: Deny rules silently bypassed because security checks cost too many tokens
This finding is one of many signals tracked across Cyber Security. The live feed updates every few hours with new authority voices, debates, and emerging ideas.
← Back to Cyber Security