find-skills
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes PowerShell and Bash code snippets to inventory directories and read file contents from standard AI agent configuration locations (~/.claude/skills/).
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from other skill definitions.
- Ingestion points: Reads name and description fields from SKILL.md files found in global and project directories.
- Boundary markers: None; extracted data is displayed to the user in a markdown table format.
- Capability inventory: Restricted to reading local configuration files and listing directory contents.
- Sanitization: Employs regex matching and string trimming to parse metadata from the headers of other skill files.
Audit Metadata