lighthouse

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

• Third-party content exposure detected (high risk: 0.90). The skill’s workflow instructs the agent to use Membrane to run actions and proxy requests against the Lighthouse service (e.g., "List Messages" / "Get Message" in the "Popular actions" table and the "membrane request ... proxy requests" section), which will return user-generated/untrusted third-party content that the agent is expected to read and could influence follow-up actions.