appbaseio

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to run Membrane actions and proxy arbitrary Appbase.io API requests (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint"), which causes the agent to fetch and read open/third‑party Appbase.io content (potentially user-generated) that can influence subsequent actions.