mcp

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly shows the MCP server calling external public APIs (for example the "get_weather" tool that fetches https://api.weather.com/current?city=...), and those untrusted third-party responses are returned to and acted on by the agent, so external content could influence tool use and decisions.