prose-critique

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed exclusively of Markdown files providing guidelines and resources for prose critique. No executable scripts (Python, Node.js, etc.) or configuration files with automated behaviors were found.
  • [SAFE]: External links found in resources/prose.md target well-known academic and research repositories (arXiv and ACL Anthology). These are used for legitimate educational purposes to explain linguistic patterns in AI-generated text.
  • [SAFE]: The skill instructs the agent to reference project-specific directories via the $MERIDIAN_FS_DIR environment variable. This is used for narrative continuity checks (timeline, character facts, canon) and represents standard, intended functionality for maintaining consistency in creative writing projects.
  • [SAFE]: No prompt injection patterns, data exfiltration mechanisms, or obfuscated content were detected across any of the files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 12:03 PM