apify-content-analytics

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md Step 4/runner/run_actor.js downloads Apify Actor dataset items (and prints them as “quick answer” or writes to CSV/JSON) without any filtering of the underlying scraped text.

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

• Potentially malicious external URL detected (high risk: 1.00). The run_actor.js script calls Apify API endpoints at runtime (e.g., https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}) to start actor runs (i.e., execute remote code) and the skill depends on those actor executions.