Apify

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

• Third-party content exposure detected (high risk: 0.90). This skill directly calls Apify actors to scrape public, user-generated content (e.g., tweets, Instagram posts, Facebook groups, Google Maps reviews, and arbitrary websites via scrapeWebsite) — see SKILL.md/INTEGRATION.md and actor files like actors/social-media/twitter.ts and actors/web/web-scraper.ts — and the integration workflows explicitly return scraped text (tweets/threads/reviews/posts) for the agent to read and act on (e.g., "Turn my latest tweet into a LinkedIn post"), so untrusted third‑party content can materially influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes remote Apify actors at runtime via the Apify API (default APIFY_API_BASE_URL=https://api.apify.com/v2 and platform endpoints like https://apify.com), causing execution of remote actor code that the skill depends on for its functionality.