writing-skills

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The utility script render-graphs.js uses child_process.execSync to execute the Graphviz dot command. This is used to transform markdown code blocks into SVG diagrams. The script safely passes content via standard input (stdin) to the dot binary, avoiding shell injection risks from the markdown content.
  • [EXTERNAL_DOWNLOADS]: The documentation references various legitimate third-party libraries and tools (such as Graphviz, pdfplumber, and docx-js) and provides standard installation instructions for system package managers (apt, brew) and package registries (npm, pip).
  • [PROMPT_INJECTION]: The skill provides defensive guidance on how to write agent instructions that are resistant to 'rationalization' or 'shortcuts.' It uses research-based psychological principles to ensure the agent adheres to strict quality standards like TDD, which enhances the reliability of the agent's output.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:11 PM
Security Audit — agent-trust-hub — writing-skills