technical-writer

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed for technical writing and documentation tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content to generate documentation. * Ingestion points: Processes documentation files in docs/ directories and README files. * Boundary markers: None explicitly defined for file reading. * Capability inventory: Primarily file writing and content organization. * Sanitization: Instructions explicitly forbid inventing information and require verification of technical accuracy, which acts as a logical filter for untrusted content.
  • [CREDENTIALS_UNSAFE]: The documentation guidelines explicitly instruct users to use placeholders for keys and warn against sharing secrets, promoting secure documentation practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:31 PM
Security Audit — agent-trust-hub — technical-writer