zenserp

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly instructs using Membrane to query the Zenserp API (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and the Search/Search Result actions) which fetches public SERP content (untrusted third-party webpages) that the agent is expected to read and act on.