starloop

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow (e.g., the "membrane action list/run" and "membrane request CONNECTION_ID /path/to/endpoint" commands in SKILL.md) lets the agent fetch and interpret data from the Starloop API — which can include untrusted, user-generated customer reviews — and those responses can directly influence the agent's subsequent actions.