to-questionnaire
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user input regarding the recipient's role, expertise, and specific requirements, which are then interpolated into a Markdown template.
- Ingestion points: User input collected during the interview steps defined in
SKILL.md. - Boundary markers: Absent; user content is placed directly into headings and paragraphs.
- Capability inventory: Writing to the local file system (
to-questionnaire-<slug>.md). - Sanitization: The instructions do not specify any validation or sanitization for the user-supplied content before it is written to the file.
- [COMMAND_EXECUTION]: The skill instructs the agent to write a Markdown file to the local directory. This is the intended behavior for generating the document based on the user's requirements.
Audit Metadata