to-questionnaire

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill reads a project routing document using a relative path (../../WORK-ROUTING.md), which is a legitimate action for maintaining repository standards.
  • [PROMPT_INJECTION]: The process of generating a questionnaire from user input creates an indirect prompt injection surface. However, this is inherent to the skill's purpose and does not include malicious directives.
  • [SAFE]: File write operations are restricted to the local directory with a specific naming convention (to-questionnaire-.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 01:31 AM
Security Audit — agent-trust-hub — to-questionnaire