brand-safety-screen

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

• Third-party content exposure detected (high risk: 1.00). The skill's Information Gathering section explicitly asks for and accepts URLs to profiles or posts and other user-generated social media content ("pasted captions and post text, URLs to profiles or posts, exported content..."), which the agent is required to scan and interpret to make risk-tiered decisions, exposing it to untrusted third-party content that could carry indirect prompt injection.