extracting-code-structure
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [Command Execution] (LOW): The skill provides instructions for executing multiple CLI tools (ast-grep, fzf, ripgrep, sd, yq) to explore and modify code structures. These are standard developer tools but operate via shell execution and piping.
- [Indirect Prompt Injection] (LOW): The skill processes untrusted code and configuration files, which could contain instructions meant to deceive the agent during exploration or refactoring. 1. Ingestion points: Source code and YAML files processed by ast-grep and yq. 2. Boundary markers: Absent. 3. Capability inventory: Shell piping, xargs, and file-writing via the sd utility. 4. Sanitization: None.
Audit Metadata