ai-ugc-ads

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

• Third-party content exposure detected (high risk: 0.72). The skill’s runtime workflow includes recruiting/using UGC from third-party creator marketplaces and creators (e.g., Billo/Insense/TikTok Creator Marketplace/Collabstr) and then ingesting their submitted video text/metadata and briefs into the agent’s context for editing/testing, which is outsider-authored free-form content.