wuf

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 to proxy arbitrary requests to the Wuf API (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint"), which fetches third-party Wuf data (potentially user-generated) that the agent is expected to read and act on.