status-hero

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md instructs the agent to fetch Status Hero data (e.g., "Check-in / Answer" items) and use Membrane proxy requests (membrane request CONNECTION_ID /path/to/endpoint and action runs) to read user-generated status updates from a third‑party service, which the agent is expected to interpret and could materially influence subsequent actions.