iblai-api-external-service-proxy

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

• Third-party content exposure detected (high risk: 0.70). High likelihood: the required workflow calls outsider network endpoints for service discovery (/orgs/{org}/services/ and /services/{service}/), and the JSON fields returned there (e.g., display_name, endpoint catalog) are then ingested by the client/agent logic into LLM context, enabling indirect prompt injection via those outsider-provided free-text fields.