avoid-ai-writing

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's research corpus management scripts fetch public domain texts and machine datasets from well-known services including Project Gutenberg and Hugging Face.
  • [COMMAND_EXECUTION]: Local Node.js scripts bundled with the skill, such as the preservation validator and style checker, are executed to verify the integrity and quality of rewrites.
  • [PROMPT_INJECTION]: The instruction file contains explicit directives to ignore instructions or metadata-based overrides embedded in the text being audited, providing a robust layer of protection against indirect prompt injection.
  • [SAFE]: The skill operates with clear safety boundaries for file modification and data processing, focusing strictly on its stated purpose without engaging in suspicious or unauthorized behaviors.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 01:38 AM
Security Audit — agent-trust-hub — avoid-ai-writing