social-media-intelligence

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and analyzes public, user-generated social media content (e.g., SocialPost.content and SocialPost.url used throughout HashtagAnalyzer, Claim.add_appearance, coordination_likelihood, and AccountAnalysis) and also fetches/archeives arbitrary third‑party URLs via SocialArchiver.archive_to_wayback and archive_to_archive_today, so untrusted external content can directly influence scoring and subsequent actions.