apify-ecommerce

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly runs an Apify e-commerce scraper (see SKILL.md "Running the Extraction" and "Supported Marketplaces") via reference/scripts/run_actor.js to fetch product pages, reviews and Google Shopping results from public sites (Amazon, Walmart, Google Shopping), and those untrusted, user-generated webpages and reviews are ingested and then analyzed (AI Summary / customPrompt and quick-answer display), which could allow indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The run_actor.js script calls the Apify API at URLs like https://api.apify.com/v2/acts/... (and dataset endpoints) at runtime to start Apify actors—which executes remote code on Apify and is a required dependency for the skill to run.