review-environments

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly pulls and installs Hub environments ("Review Input Modes" — "Pulled Hub environment via prime env pull owner/name" and subsequent prime env install / prime eval run steps), meaning it fetches untrusted, user-contributed third-party code/content that the agent must read/execute as part of the review and which can materially influence tool use and decisions.