writing-skills

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/render-graphs.js script utilizes the Node.js execSync function to execute the dot command-line utility. This is a legitimate utility function used to render Graphviz diagrams embedded in the skill documentation.
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests the installation of the graphviz system package via standard package managers like Homebrew or APT to enable diagram rendering. This is a documented dependency for the skill's auxiliary tooling.
  • [PROMPT_INJECTION]: The guides references/persuasion-principles.md and references/rationalization-patterns.md discuss the use of assertive language and behavioral psychology to ensure agent compliance with technical workflows. While these are advanced prompt engineering techniques for steering agent behavior, they are presented as organizational best practices for process discipline rather than malicious exploits or safety bypasses.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 06:36 PM