agent-md-refactor
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's logic is restricted to reading, analyzing, and restructuring local markdown files within the project directory. It does not perform any network operations, access sensitive system paths, or execute external code.
- [PROMPT_INJECTION]: The instructions focus purely on the refactoring process and do not contain patterns intended to bypass safety filters or override the agent's core behavior.
- [DATA_EXFILTRATION]: No network calls or data exfiltration patterns were detected. The skill interacts only with local project documentation files as intended and does not access sensitive credentials or environment variables.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided documentation files (e.g., CLAUDE.md). While these are external inputs, the risk is inherent to documentation processing and the skill's purpose is structural reorganization. * Ingestion points: Reads CLAUDE.md, AGENTS.md, or COPILOT.md. * Boundary markers: None specified. * Capability inventory: File system read and write operations within the project directory. * Sanitization: None specified.
Audit Metadata