erxes

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 explicitly instructs the agent to fetch and operate on data from an external Erxes instance (e.g., via "membrane action list", "membrane action run", and "membrane request CONNECTION_ID /path/to/endpoint"), which exposes user-generated third-party content that the agent is expected to read and that can influence subsequent actions.