scoopit

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 connect to Scoop.it via the Membrane CLI (e.g., "membrane connect --connectorKey scoopit" and "membrane action run ") and to retrieve/manage Scoop.it content, which is user-curated/third‑party content the agent will ingest and act on, exposing it to untrusted external content.