to-questionnaire
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate a document.
- Ingestion points: User responses regarding the recipient's role and specific information needs are collected in steps 1 and 2 within SKILL.md.
- Boundary markers: The skill does not implement boundary markers or instructions to treat embedded user content as data only.
- Capability inventory: The skill writes a Markdown file (to-questionnaire-.md) to the local file system based on a template.
- Sanitization: There are no instructions provided to sanitize, escape, or validate the user-supplied strings before they are written to the file.
Audit Metadata