AI Influencer Generation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs sending arbitrary external image URLs via the "image_urls" parameter (see "Using Reference Images" and multiple examples) which the each::sense API will fetch and use to guide generations, meaning untrusted third-party content can be ingested and influence model outputs.