do-improve-doc
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading markdown documents provided by the user at a specified path. Maliciously crafted documentation could include instructions designed to override the agent's behavior during the analysis or refinement phases.
- Ingestion points: The full contents of the file at the user-provided
Pathare loaded in Phase 1, Step 1 ofSKILL.md. - Boundary markers: There are no explicit instructions or delimiters used to separate the document content from the agent's internal logic, making it difficult to distinguish between data and instructions.
- Capability inventory: The skill has the capability to write to the local file system (Step 4 of Phase 2), providing a potential impact path if the agent is successfully injected.
- Sanitization: No sanitization, escaping, or filtering of the external file content is performed before it is processed by the model.
Audit Metadata