grill-me
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to use standard CLI tools including
fd,ast-grep,git grep, andbatto gather context from the local codebase. These tools are used in a read-only capacity to facilitate software design analysis and codebase exploration. - [SAFE]: A comprehensive analysis of the skill's instructions, metadata, and tool contracts revealed no evidence of prompt injection, data exfiltration, or obfuscation. The skill maintains a clear boundary between the agent and user, requiring explicit confirmation for each step in the design process.
Audit Metadata