mcp-builder

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

• Third-party content exposure detected (high risk: 0.70). The required workflow is to read the target API’s documentation (e.g., OpenAPI spec/README/changelog) during Phase 1, which is typically fetched from public web sources or third-party repos at runtime and can include outsider-authored free text that the agent would ingest into the LLM context.