apify-audience-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill runs Apify actors that scrape public social platforms (see SKILL.md actor list: Facebook/Instagram/YouTube/TikTok) and its run_actor.js explicitly fetches and downloads dataset items from https://api.apify.com/v2/datasets/... (downloadResults/displayQuickAnswer) and also fetches actor schemas via mcpc from mcp.apify.com, so untrusted, user-generated third‑party content is ingested and then read/summarized by the agent as part of its workflow—allowing embedded instructions to influence outputs.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes Apify API endpoints at runtime (e.g., https://api.apify.com/v2/acts/{author~actor}/runs?token=...) to start third-party Actors that execute remote code and are required for the skill to operate.