ast-grep

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for using the ast-grep command-line tool to perform structural matching on codebases. It includes examples of running ast-grep run and ast-grep scan with various parameters to find specific code constructs.\n- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it involves processing external code from user-defined project directories.\n
  • Ingestion points: Source code files read by the ast-grep tool from the local filesystem during a search operation.\n
  • Boundary markers: No explicit delimiters or instructions are provided to distinguish codebase content from agent instructions during the analysis of search results.\n
  • Capability inventory: The skill leverages the ast-grep CLI for structural search and encourages creating temporary files for testing rules.\n
  • Sanitization: There is no evidence of content sanitization or filtering for the code snippets matched by the search rules before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 04:11 AM