tech-writing

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a specific writing persona and stylistic constraints for technical documentation, blog posts, and READMEs.- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface by processing external repository content, though no malicious exploitation was found.
  • Ingestion points: Processes any content in repositories, including READMEs, docs, and blog posts (as specified in SKILL.md).
  • Boundary markers: None present for the ingested content.
  • Capability inventory: Uses file reading and the GitHub CLI (gh) to verify data against repositories and PR lists.
  • Sanitization: None specified for the content being processed or verified.- [SAFE]: No malicious command execution, exfiltration, or obfuscation was detected. The use of gh pr list for verification is standard developer tooling and is used here in a safe, descriptive context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 08:27 PM
Security Audit — agent-trust-hub — tech-writing