claude-design-system
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to manage local design assets by reading from an
/inspirationdirectory and writing to a/generateddirectory. It does not access sensitive system paths or user credentials. - [SAFE]: No network activity was detected. The skill does not use tools like curl or wget, nor does it attempt to exfiltrate any data to external servers.
- [SAFE]: Although the skill generates React and Tailwind CSS code, it functions as a code generator rather than an execution engine. It does not attempt to compile or run the generated code, nor does it perform automated package installations.
- [SAFE]: The skill logic includes a mandatory discovery phase and strict rules regarding output formatting (e.g., forbidding emojis), which are standard instructional constraints rather than malicious prompt injections.
- [SAFE]: While the skill ingests filenames and markdown content which could theoretically serve as an indirect injection vector, the agent lacks high-privilege capabilities (such as shell access or network connectivity) that would allow such an injection to result in a security compromise.
Audit Metadata