kol-engager-icp

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly scrapes user-generated LinkedIn content (posts, reactions, comments, and profiles) via Apify actors (harvestapi/linkedin-profile-posts, harvestapi/linkedin-company-posts, harvestapi/linkedin-profile-scraper) as described in SKILL.md and scripts/kol_engager_icp.py, and it directly reads and interprets that third‑party content (post text, comments, headlines) to select posts, score engagers, and drive enrichment and classification decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill invokes external Apify actors at runtime via the Apify API (e.g., https://api.apify.com/v2/actor-runs/... and the Gooseworks proxy https://api.gooseworks.ai) to run remote scraping/enrichment actors (harvestapi/...), which executes remote code during runtime and is a required dependency.