skills/bighardperson/computer-science-skills-collection/document-multiple-repository/Gen Agent Trust Hub
document-multiple-repository
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs recursive scans and reads content from untrusted local repository files including READMEs, Wikis, and manifest files to generate consolidated documentation. This creates an attack surface where malicious instructions embedded in a repository's documentation could influence the agent's behavior during the consolidation process.
- Ingestion points: Recursive file system scan of ROOT_PATH targeting .git folders, READMEs, and .wiki repositories.
- Boundary markers: No explicit delimiters or 'ignore instructions' warnings are defined for the interpolation of external repository content into the final documentation.
- Capability inventory: The skill performs local file read operations and writes generated documentation to OUTPUT_PATH. It does not have network or command execution capabilities.
- Sanitization: There is no evidence of sanitization or filtering applied to the content extracted from the processed repositories.
Audit Metadata