claude-skill-spec-audit
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local file system operations to glob and read 'SKILL.md' files in specific directories (
~/.claude/skills/). This is standard behavior for a configuration auditing tool. - [DATA_EXFILTRATION]: No network operations or external data transmissions are present. The skill processes information locally and reports findings to the user.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts or external packages.
- [SAFE]: The 'fix' functionality is limited to editing YAML frontmatter fields in skill definition files based on pattern matching and user input.
Audit Metadata