qalam
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests source code from the local file system to generate documentation, presenting an attack surface for indirect instructions embedded in code comments.
- Ingestion points: Reads source files (Python, JS, TS) from user-provided paths.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore natural language instructions found within code comments or docstrings.
- Capability inventory: The tool writes new documentation files and has the capability to modify source files when generating docstrings.
- Sanitization: No validation or sanitization of the extracted comment text is mentioned before it is processed by the agent.
Audit Metadata