flipando

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly lets the agent fetch and run Flipando API/app content via Membrane (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and actions like "flipando.get-app" / "flipando.run-app"), which exposes user-created/untrusted Flipando content that the agent is expected to read and act on, so third-party content could indirectly inject instructions.