help
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes a dynamic discovery process to scan the 'src/skills' directory for user-invocable skills. This approach ensures that the help menu reflects the current state of the repository without relying on stale, hardcoded lists.
- [SAFE]: All tool usage (Grep, Read, AskUserQuestion) is restricted to local file operations and user interaction, with no network connectivity or data exfiltration paths identified.
- [SAFE]: No obfuscation, prompt injection attempts, or unauthorized command execution patterns were found within the skill's instructions or metadata.
- [SAFE]: The skill correctly identifies and lists built-in Claude Code commands, providing helpful context for users without attempting to override or modify agent behavior.
Audit Metadata