to-questionnaire

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs routine documentation generation and does not exhibit any malicious patterns.
  • [COMMAND_EXECUTION]: The skill instructs the agent to create a local Markdown file using a slug-based filename (to-questionnaire-<slug>.md). This is a standard functional requirement for documentation tools and does not pose a security threat.
  • [DATA_EXFILTRATION]: No network communication or unauthorized access to sensitive data was detected. All processed information is provided by the user or derived from the immediate project context.
  • [PROMPT_INJECTION]: The instructions are focused on a specific task workflow and do not contain patterns typical of prompt injection or safety bypass attempts.
  • [SAFE]: Regarding potential injection surfaces, the skill ingests user input to populate a document (ingestion points: SKILL.md steps 1-2). While explicit boundary markers are absent, the skill's capabilities are limited to writing local Markdown files (capability inventory: SKILL.md step 3), and it uses filename slugging (sanitization: SKILL.md step 3), presenting a very low risk surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:56 PM
Security Audit — agent-trust-hub — to-questionnaire