apify-influencer-discovery

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

• Third-party content exposure detected (high risk: 0.75). Yes—at runtime the workflow fetches outsider-authored free text from Apify actor outputs (public dataset items / actor README content) via fetch in reference/scripts/run_actor.js, then prints it to chat (quick answer) which becomes LLM-visible context.

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

• Potentially malicious external URL detected (high risk: 0.90). run_actor.js makes runtime POST/GET calls to the Apify API (e.g., https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}) which start and poll Apify actors (i.e., execute remote code) and are required for the skill to function.