NYC

grepai-mcp-cursor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): This skill contains only markdown documentation and configuration examples. No scripts (.py, .js, .sh) or executable files are included.
  • [Command Execution] (SAFE): The skill provides instructions for running local commands (grepai) and configuring an MCP server. These are standard operations for the tool's intended purpose and do not involve unauthorized execution.
  • [Credentials Unsafe] (SAFE): The documentation includes a placeholder for an API key (sk-...) but correctly follows best practices by advising users to use environment variables instead of hardcoding secrets.
  • [Data Exfiltration] (SAFE): No unauthorized network activity was detected. Troubleshooting steps use curl to check local services (localhost).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:03 PM