avoid-ai-writing

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or data exfiltration vectors were detected. The skill's functionality is strictly limited to text manipulation and writing style improvement.
  • [SAFE]: The software incorporates internal security-conscious features such as the 'normalizeText' function in 'detector/patterns.js', which identifies and strips zero-width characters and homoglyph substitutions to prevent bypass attempts.
  • [SAFE]: External references and installation instructions are consistent with established open-source development practices, pointing exclusively to the author's official GitHub repository.
  • [SAFE]: The skill uses the platform's standard file-editing capabilities responsibly, including specific instructions to preserve quoted material, code blocks, and human-authored passages during processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:05 AM
Security Audit — agent-trust-hub — avoid-ai-writing