writing-skills

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The utility script references/render-graphs.js executes the system command dot (Graphviz) using Node.js child_process.execSync. This functionality is used to render architectural and process flow diagrams defined in Markdown into SVG images for visualization.
  • [PROMPT_INJECTION]: The methodology detailed in references/persuasion-principles.md and references/testing-skills-with-subagents.md advocates for the use of high-authority imperative language (e.g., "YOU MUST", "No exceptions"). These techniques are employed as a design pattern to ensure agents strictly adhere to critical procedural rules and resist rationalization during high-pressure tasks.
  • [EXTERNAL_DOWNLOADS]: The skill references official documentation and resources from anthropic.com and agentskills.io. These are trusted sources for platform specifications and best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 05:12 AM