document-this
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user's codebase (source files, tests, and configurations) to generate documentation. If these files contain malicious instructions in comments or code, the agent might follow them during the prose generation phase.
- Ingestion points: Multiple scripts (
entities.mjs,entry_points.mjs,fingerprint.mjs,tech_stack.mjs,test_inventory.mjs) read file content from the project directory. - Boundary markers: The skill does not implement specific delimiters or instructions to the agent to ignore potentially malicious prompts embedded within the analyzed code comments or strings.
- Capability inventory: The agent has the ability to read the entire project structure and write documentation files to the local disk. The scripts themselves emit JSON to stdout for the agent to process.
- Sanitization: The skill relies on the agent's interpretation of the extracted data without explicit sanitization or filtering of the source content.
Audit Metadata