muapi-award-ceremony-video

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md requires user-supplied image URLs (winner_image and host_image) that the agent will fetch and pass to the muapi endpoint (and whose order directly controls role assignment and generated behavior), so untrusted public images can be ingested and materially influence generation.