add-integration

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries public third‑party sources (e.g., the npm registry and MCP server directories) and ingests package metadata/descriptions to choose and generate .mcp.json configurations, so untrusted user-generated content from those sources could materially influence tool selection and next actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly uses npx to run pre-built MCP packages (which will fetch and execute code from the npm registry, e.g. https://registry.npmjs.org/) at runtime, so external code is executed and relied upon for the integration.