library-craft
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a passive code analysis tool. It reads project files like package.json, source code, and READMEs to generate architectural reviews.
- [SAFE]: Explicit safety rules are defined in the instructions to prevent the agent from editing source files or publishing any data (comments, issues, or releases) without explicit user permission.
- [SAFE]: The ecosystem comparison workflow uses a subagent prompt template for research, which is a standard analytical behavior with no detected malicious intent.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized remote code execution was found across the skill and its referenced files.
Audit Metadata