manage-mcp

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

• Third-party content exposure detected (high risk: 0.70). The skill's resource and tool examples explicitly fetch open web APIs (e.g., "Create API Resource" with $fetch('https://api.example.com/users') and the "Weather API Integration" tool calling https://api.weather.com/...), which cause the agent to ingest and act on third‑party content as part of its workflow.