omada-controller

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to fetch and parse the controller's live OpenAPI spec (GET {OMADA_URL}/v3/api-docs) and use it to discover endpoints at runtime, so the agent will ingest and act on externally hosted controller content that can materially change which API calls it makes.