writing-skills
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Node.js utility script,
render-graphs.js, which usesexecSyncto run system commands such asdot(Graphviz) andwhich. This script is designed to extract Graphviz diagrams from the skill documentation and render them as SVG files.- [DYNAMIC_EXECUTION]: Therender-graphs.jsscript performs runtime file system operations, including readingSKILL.mdfiles and writing rendered diagrams to adiagrams/directory.- [EXTERNAL_DOWNLOADS]: The documentation (specificallyanthropic-best-practices.mdandSKILL.md) references several third-party libraries and tools, such aspdfplumber,pypdf,pytesseract, andgraphviz, as examples for specific technical implementations.- [PROMPT_INJECTION]: The skill utilizes 'Persuasion Principles' (e.g., Authority, Commitment) and 'Bulletproofing' strategies to enforce strict adherence to developer workflows like TDD. These instructions use strong imperative language ("YOU MUST", "Delete means delete") to override the agent's internal reasoning or 'rationalization' during tasks, acting as a form of discipline enforcement rather than a malicious bypass of safety filters.
Audit Metadata