muapi-action-figure-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests an arbitrary user-supplied image URL (the user_image reference in Phase A / Action Figure Generation) and uses that untrusted third-party content as the primary input to guide generation, so content in the image could indirectly influence model behavior.