writing-skills
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The utility script
render-graphs.jsusesexecSyncto invoke the system's Graphvizdotcommand. The implementation is secure as it pipes input via stdin and uses a hardcoded command string, preventing command injection vulnerabilities. - [DYNAMIC_EXECUTION]: The skill includes a Node.js script that dynamically extracts graph definitions from markdown code blocks and processes them into SVG images. This is an intended helper function for visualizing process flows.
- [PROMPT_INJECTION]: The documentation (
persuasion-principles.mdandtesting-skills-with-subagents.md) explicitly utilizes techniques such as 'Authority' and 'Commitment' framing to enforce strict compliance with TDD rules. While this involves forceful instructions and role-play scenarios, they are used defensively to prevent agent rationalization of poor coding practices rather than to bypass platform safety guardrails.
Audit Metadata