ro-innovation

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 list and run Membrane actions and to use "membrane request CONNECTION_ID /path/to/endpoint" (proxying to the Ro Innovation API), which clearly fetches and ingests content from a third-party/user-generated Ro Innovation service that the agent is expected to read and act on—opening a path for indirect prompt injection.