ast-grep
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
ast-grepCLI commands such asast-grep scanandast-grep runto analyze local codebases. These commands are standard for the tool's operation and are used to perform structural search and analysis on project files or piped input. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external codebases and files provided by the user. While the primary function is structural matching, processing untrusted source code could expose the agent to adversarial patterns embedded in the code (e.g., comments designed to influence the agent's summary of findings). The skill mitigates this by focusing on structural AST patterns rather than free-text interpretation.
Audit Metadata