cosmic

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads content from Cosmic buckets (e.g., cosmic.objects.find / cosmic.media.find and use of media URLs and reference_images such as in cosmic.ai.generateText/media_url and generateImage/reference_images), which are third-party CMS-hosted, user-generated content that the agent would ingest and interpret.