grep-app

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). In scripts/mcpcall.py, the required workflow searchGitHub sends user-supplied query/filters to the grep.app MCP (SERVER_URL = "https://mcp.grep.app"), and at runtime prints any item.text returned from grep.app, which originates from reading outsider-authored public GitHub code/files without selecting a specific trusted item first.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime script (scripts/mcpcall.py) connects to and uses the remote MCP server at https://mcp.grep.app (SERVER_URL) to invoke tools via session.call_tool, which executes remote tool code and returns results that the skill relies on.