Document Generator
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data to generate documents, which creates a vulnerability surface where malicious instructions could be embedded in the input.
- Ingestion points: The skill accepts data as input for document generation as described in the 'Critical Rules' section of SKILL.md.
- Boundary markers: No delimiters or instructions are provided to separate untrusted input data from the generation logic.
- Capability inventory: The skill utilizes libraries capable of file system writes (generating .pdf, .docx, .xlsx, .pptx).
- Sanitization: There are no instructions for sanitizing or validating input data before it is processed by document generation engines.
- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate and provide execution scripts to the user.
- Evidence: The 'Communication Style' section in SKILL.md instructs the agent to 'Provide the generation script AND the output file'.
Audit Metadata