writing-skills

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill uses directive language and 'persuasion principles' (such as Authority, Commitment, and Scarcity) intended to override an agent's default behavior and prevent the 'rationalization' of instructions. The files 'persuasion-principles.md' and 'testing-skills-with-subagents.md' provide strategies for 'bulletproofing' skill instructions against agent disobedience.
  • [COMMAND_EXECUTION]: The render-graphs.js utility script utilizes child_process.execSync to invoke the system's dot command from the Graphviz suite. It extracts content from SKILL.md and pipes it to the external process to generate SVG diagrams.
  • [EXTERNAL_DOWNLOADS]: The documentation file anthropic-best-practices.md includes references to static image assets hosted on mintcdn.com. These are used as illustrative diagrams within the skill's documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:27 AM