writing-skills

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The helper script render-graphs.js uses child_process.execSync to invoke the system's dot command (from the Graphviz suite). This is used to convert markdown-embedded DOT diagrams into SVG visualizations for documentation. It also uses which dot to verify the tool's presence on the host system.
  • [PROMPT_INJECTION]: The skill uses strong, imperative language and psychological persuasion principles (such as 'Authority' and 'Commitment') designed to ensure the agent adheres to strict documentation standards. Patterns like 'YOU MUST', 'No exceptions', and 'Delete means delete' are used as pedagogical tools to prevent agents from skipping quality-enforcement steps like testing.
  • [EXTERNAL_DOWNLOADS]: The anthropic-best-practices.md file contains image assets hosted on mintcdn.com, which is an official content delivery network for Anthropic. These resources are used for illustrative purposes in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 08:40 AM