apify-competitor-intelligence

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

• Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly directs running Apify actors that scrape public/user-generated sites (Google Maps, Booking.com, Facebook, Instagram, YouTube, TikTok), and reference/scripts/run_actor.js fetches and displays dataset items from https://api.apify.com/v2/datasets/... so the agent ingests untrusted third-party content (scraped posts/comments/reviews) that can materially influence its analysis and actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime API calls to https://api.apify.com (e.g., POST to https://api.apify.com/v2/acts/{actor}/runs?token=...) to start Apify actors which execute remote actor code and the skill depends on that external service.