to-questionnaire

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate document generation functionality. It uses a template-based approach to structure user-provided information into a questionnaire file.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests user input to populate a file.
  • Ingestion points: User-provided descriptions of the recipient and the required facts/decisions in SKILL.md (Steps 1 and 2).
  • Boundary markers: The skill uses a structured Markdown template (<questionnaire-template>) and headings to organize content.
  • Capability inventory: The skill is instructed to write a Markdown file to the current working directory (SKILL.md Step 3).
  • Sanitization: No explicit sanitization of user-provided strings is performed, but the output is a static text document intended for human review.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 09:33 AM
Security Audit — agent-trust-hub — to-questionnaire