socialhub

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests public, user-generated content — e.g., "Competitor scraping (Apify)" and "Meta Ad Library winning ads" under Competitive Intelligence and "Unified comments across platforms" / engagement scraping in the Planned Features and Workers sections of SKILL.md — which the agent is expected to read and use to drive hashtag selection, analytics, approvals, and reply suggestions, creating a clear path for indirect prompt injection.