agents-md
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill does not contain any malicious patterns or commands. Its operations are restricted to generating markdown documentation based on repository structure.- [DATA_EXFILTRATION] (SAFE): No network activity or access to sensitive local files (like SSH keys or environment variables) was detected.- [REMOTE_CODE_EXECUTION] (SAFE): The skill provides command templates (e.g., for Gradle or bun) but does not download or execute any external scripts.- [INDIRECT_PROMPT_INJECTION] (LOW): The skill inventories the repository to create documentation, representing a data ingestion surface. However, it does not execute content found in files and limits itself to summarizing structure. [Evidence Chain]: 1. Ingestion points: Repository inventory of directories and build files (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: File-write for markdown creation. 4. Sanitization: Absent.
Audit Metadata