ygy

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 using Membrane to run actions and to proxy arbitrary requests to the Y.gy API (e.g., "membrane action run ...", "membrane request CONNECTION_ID /path/to/endpoint"), which clearly fetches and ingests third-party Y.gy content that the agent is expected to read and could materially influence subsequent actions.