setup-linux-host-backend

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the workflow reads provider responses from observe auth status, observe content host view, and observe datastream list (pasted back by the user) and treats them as untrusted output via the wrap mechanism, meaning outsider-authored free text can enter the LLM context through those monitored tenant resources.