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
Risk Level
SAFE
Analyzed
Sep 22, 2026, 11:39 PM
Security Audit — agent-trust-hub — to-questionnaire