cascade-strategy

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

• Third-party content exposure detected (high risk: 0.80). This skill uses the Membrane CLI to fetch user-generated Cascade Strategy data (see SKILL.md examples like membrane action list --connectionId=... --intent "QUERY" and actions such as "List Goals" / "List Updates" that "Fetch goals" from Cascade Strategy), so the agent ingests and is expected to read/interpret untrusted third‑party content which could materially influence actions.