apify-hello-world

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs running public Apify Actors (e.g., apify/website-content-crawler) with arbitrary startUrls (examples: https://docs.apify.com/academy, https://example.com) and then retrieves and processes the crawled dataset items, which means it fetches untrusted, user-generated or public web content that the agent is expected to read/interpret as part of its workflow and could therefore contain instructions influencing subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes Apify Actors at runtime (e.g., client.actor('apify/website-content-crawler').call(...)), which causes remote code to run on Apify's API (e.g., https://api.apify.com / apify.com/store) — a required runtime dependency that executes external code outside the agent.