building-with-tambo

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

• Third-party content exposure detected (high risk: 0.90). The skill's Tools and Context instructions (references/tools-and-context.md) require wiring external MCP servers and implementing listResources/getResource (e.g., fetchDocs/fetchDocument) so the agent will fetch and read arbitrary external/document resources that can influence AI behavior, exposing it to untrusted third‑party content.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill includes a runtime mcpServers configuration (example url: "http://localhost:8123/") passed into TamboProvider and the MCP servers are explicitly described as supplying "tools, resources, prompts" — i.e., externally fetched content that can directly control agent prompts at runtime.