grep-app

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill communicates with an external MCP server at https://mcp.grep.app. This is a well-known service for code search and matches the stated purpose of the skill.
  • [COMMAND_EXECUTION]: The skill uses a Python script to call the MCP tool. The script processes command-line arguments to construct the tool call, but it does not execute arbitrary shell commands or use dangerous functions like eval() or os.system().
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests search results from GitHub repositories. While these results contain external code, the skill functions as a search tool and does not pipe this content directly into dangerous execution sinks. Standard LLM boundaries apply.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 02:10 AM