to-questionnaire

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's functionality is limited to an interactive dialogue and writing a Markdown file to the local directory. No malicious behaviors such as credential theft, obfuscation, or remote code execution were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information and interpolates it into a document template.
  • Ingestion points: The interview process where the user provides information about the recipient and the required data (SKILL.md).
  • Boundary markers: None; the user's responses are placed directly into the Markdown template structure.
  • Capability inventory: The skill uses a file-writing capability to create a Markdown document in the local directory (SKILL.md).
  • Sanitization: No input sanitization or explicit escaping is defined for the user-supplied strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:27 AM
Security Audit — agent-trust-hub — to-questionnaire