to-questionnaire
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding a decision or topic to generate a markdown document. While this creates a surface where untrusted data is written to a file, the impact is restricted to the generated document. Ingestion points: User descriptions of the recipient and the information gap as defined in SKILL.md. Boundary markers: None explicitly mentioned in the file-writing instructions. Capability inventory: Local file-write operations to to-questionnaire-slug.md. Sanitization: No specific validation or escaping of user-provided content is mentioned.
- [EXTERNAL_DOWNLOADS]: The ATTRIBUTION.md file provides a reference to the upstream source repository on GitHub for licensing and attribution purposes. This link is informational, and no runtime downloads or remote code executions are performed from this URL.
Audit Metadata