writing-skills

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill documentation describes 'Persuasion Principles' (such as Authority and Commitment) to ensure agents follow strict development rules like Test-Driven Development. While these involve strong imperative language ('YOU MUST', 'No exceptions'), they are used here as a legitimate design pattern for enforcing technical discipline rather than for malicious subversion.
  • [COMMAND_EXECUTION]: The render-graphs.ts script utilizes child_process.execSync to run the system's Graphviz dot utility. This command is used locally to convert DOT syntax in markdown files into SVG diagrams, with input handled via stdin to mitigate shell injection risks.
  • [EXTERNAL_DOWNLOADS]: The documentation references external tools and libraries, including Graphviz and Python packages like pdfplumber and pypdf, as optional dependencies for specific skill-authoring patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 09:55 PM
Security Audit — agent-trust-hub — writing-skills