badger-maps

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

• Third-party content exposure detected (high risk: 0.80). The skill’s SKILL.md instructs the agent to fetch and run actions against external Badger Maps data (e.g., using "membrane action run --connectionId=CONNECTION_ID ACTION_ID" and "membrane request CONNECTION_ID /path/to/endpoint"), which ingests untrusted third‑party/user-generated records (customers, leads, check‑ins) that the agent is expected to read and could materially influence subsequent actions.