apify-content-analytics

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

• Third-party content exposure detected (high risk: 0.90). The skill starts Apify actors that scrape public social media (Instagram, Facebook, YouTube, TikTok) and then downloads and displays dataset items from the Apify dataset endpoint (https://api.apify.com/v2/datasets/{datasetId}/items) — e.g., the displayQuickAnswer function prints scraped, user-generated content into chat — so it clearly ingests untrusted third‑party content that could carry indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime calls to Apify endpoints (e.g., via mcpc to mcp.apify.com to fetch actor schemas and the run script POSTs to https://api.apify.com/v2/acts/.../runs and downloads from https://api.apify.com/v2/datasets/...), which are required at runtime and actually start/drive remote Apify actors (i.e., execute remote code) and can directly determine what runs and data the agent uses.