avoid-ai-writing

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill consists solely of markdown instructions and does not contain any executable scripts, binaries, or platform-specific command calls.
  • [EXTERNAL_DOWNLOADS]: The skill references the brandonwise/humanizer GitHub repository as an informational source for its vocabulary lists. It does not perform any automated downloads, package installations, or remote script execution.
  • [PROMPT_INJECTION]: The skill provides structured instructions for auditing and rewriting text. It includes specific logic for a 'detect' mode versus a 'rewrite' mode and implements a 'self-reference escape hatch' to correctly handle quoted text examples. None of these instructions attempt to bypass the underlying agent's safety protocols or system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 01:28 PM
Security Audit — agent-trust-hub — avoid-ai-writing