agents-md
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses find and ls to discover local skill files and ln to manage symbolic links for documentation files within the project root. These actions are standard for project documentation management and do not target sensitive system files.
- [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by reading local documentation files, though this is its primary intended function. • Ingestion points: Reads SKILL.md files located in .claude/skills and plugins directories. • Boundary markers: No explicit delimiters or ignore instructions are specified for parsing these files. • Capability inventory: The agent is tasked with writing to AGENTS.md and creating symbolic links. • Sanitization: Content from the discovered skills is not sanitized before being incorporated into the agent-facing documentation.
Audit Metadata