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 media (see SKILL.md actor list like apify/instagram-comment-scraper) and the runtime script (reference/scripts/run_actor.js) explicitly fetches and ingests dataset items from Apify API endpoints (e.g., downloadResults/displayQuickAnswer calling https://api.apify.com/v2/datasets/${datasetId}/items), so the agent will read and act on untrusted, user-generated third‑party content.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill makes runtime calls to Apify endpoints (e.g., the mcpc call to mcp.apify.com and API requests like POST to https://api.apify.com/v2/acts/{actorId}/runs?token=...) which fetch actor schemas that drive prompts and/or start remote Apify actors (i.e., execute remote code), so these URLs are runtime dependencies that can control prompts or trigger code execution.