to-questionnaire

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it interpolates user-provided data into a generated Markdown file without sanitization.
  • Ingestion points: User inputs defining the recipient role and specific decisions/facts required are gathered in SKILL.md.
  • Boundary markers: The provided document template does not include delimiters or instructions to ignore potential commands within the user-supplied text.
  • Capability inventory: The skill is granted file-writing capabilities to create the 'to-questionnaire-.md' file in the current directory.
  • Sanitization: There is no logic provided to escape or validate user inputs before they are persisted to the filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 12:24 AM
Security Audit — agent-trust-hub — to-questionnaire