ritekit

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 call Ritekit APIs and to proxy arbitrary Ritekit endpoints via Membrane (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and "Get URL Metrics"), which fetches external/public Ritekit data (often derived from social media/public URLs) that the agent is expected to read and use to decide next actions.