ig-ops-pipeline

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

• Third-party content exposure detected (high risk: 1.00). The skill's ig-trend-scanner explicitly scrapes competitor Instagram posts via Apify ("ig-trend-scanner: Apify scrape + Claude") and ig-lead-scorer extracts commenters for scoring via Claude—both ingest untrusted, user-generated social-media content that the agent analyzes and upserts into style_library/ig_lead_scores and thus can materially influence downstream decisions.