writing-skills
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The
render-graphs.jsscript executes system commands such aswhich dotanddot -TsvgusingexecSync. This is a functional requirement for rendering Graphviz diagrams defined within the skill's documentation blocks. - [DYNAMIC_EXECUTION]: The skill includes a local Node.js utility (
render-graphs.js) that spawns external processes at runtime to handle Graphviz diagram generation. The input to these processes is handled via standard input, which is a standard pattern for this type of utility. - [PROMPT_INJECTION]: The skill and its methodology (documented in
persuasion-principles.mdandtesting-skills-with-subagents.md) utilize authoritative language and psychological triggers like commitment and scarcity. These are presented as a methodology for improving the reliability and rule-adherence of AI agents during complex development tasks, rather than for malicious subversion of platform safety filters.
Audit Metadata