nsfw-content-generation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and references/SSE-EVENTS.md show the agent posts to the third-party endpoint https://sense.eachlabs.run/chat, accepts arbitrary image_urls and streams Server-Sent Events (including "thinking_delta" and "status" events) from that external service, so untrusted third-party content (public URLs and API responses) is ingested and can influence subsequent tool use and decisions.