distributing-omnichannel-content

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly asks the user to provide a core piece of content as "text, a URL, or a document" and then analyzes that source material, meaning it can fetch and interpret arbitrary public web content or user-supplied third-party material (e.g., blog posts or URLs) which could carry untrusted instructions.