how
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a developer tool for explaining and critiquing codebase architecture. It employs a multi-agent structure where subagents are provided with role-specific templates and instructions to operate under a read-only contract, ensuring they do not mutate the system or exfiltrate data.\n- [COMMAND_EXECUTION]: The skill utilizes
rg(ripgrep) for searching codebase symbols and call chains. This is a standard and safe use of command-line tools for the purpose of code exploration.\n- [PROMPT_INJECTION]: The skill uses templates to interpolate user-provided questions and codebase content into prompts for subagents. While this creates an indirect prompt injection surface, it is a functional requirement for code analysis and is mitigated by the structured role definitions and explicit boundaries provided in the reference prompt templates.
Audit Metadata