documentation-writer
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source code and project metadata to generate documentation, creating a potential ingestion surface for indirect instructions hidden in comments or code strings.
- Ingestion points: Source code, API definitions, and project metadata provided by the user for documentation.
- Boundary markers: Absent; the prompt lacks specific delimiters or instructions for the agent to disregard instructions embedded within the source data.
- Capability inventory: The skill is designed to read and document project structure, requiring access to the project's files via agent tools.
- Sanitization: None; the instructions do not define any validation or filtering of the source content before it is processed.
Audit Metadata