writing-skills
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
render-graphs.jsutility script useschild_process.execSyncto execute the systemdotcommand (Graphviz). It extracts Graphviz definitions from markdown code blocks within the documentation and pipes them to the renderer to produce SVG diagrams.\n- [PROMPT_INJECTION]: The skill instructions and thepersuasion-principles.mdfile describe techniques for using authoritative and imperative language (e.g., 'YOU MUST', 'No exceptions', 'Delete it') to steer agent behavior and prevent rationalization of skipped steps. While these are strong behavioral instructions, they are intended to enforce legitimate development processes like TDD rather than to bypass platform safety guardrails.
Audit Metadata