writing-skills
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The utility script
render-graphs.jsuseschild_process.execSyncto run the system commanddot(Graphviz) for rendering diagrams. It operates on local files within the skill directory. - [PROMPT_INJECTION]: Test scenarios in
testing-skills-with-subagents.mduse strong instructional framing like "IMPORTANT: This is a real scenario" to evaluate agent adherence to procedural rules. In the context of the skill's TDD methodology, these are benign testing instruments. - [DYNAMIC_EXECUTION]: The skill uses a script to dynamically convert Graphviz definitions in
SKILL.mdinto SVG assets, facilitating visualization without malicious runtime code generation.
Audit Metadata