to-questionnaire
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided information through interactive dialogue to populate a questionnaire template. While it lacks explicit sanitization or boundary markers for the ingested data, the risk is minimal as the output is a static Markdown file intended for human-to-human communication. Evidence: Ingestion point (SKILL.md interaction), Capabilities (file writing), Sanitization (none), Boundary markers (none).
- [COMMAND_EXECUTION]: The skill directs the agent to write a file named to-questionnaire-.md to the local directory. This file system interaction is the primary intended function of the skill and does not involve the execution of the written content or access to sensitive system paths.
Audit Metadata