apify-ecommerce

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

• Third-party content exposure detected (high risk: 0.85). The required runtime path downloads Apify dataset items (which contain scraped product/review/seller text from outsider-authored e-commerce pages) via downloadResults() / displayQuickAnswer() calling https://api.apify.com/v2/datasets/${datasetId}/items?...&format=json, and those text fields are then surfaced to the agent/LLM for summarization.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime calls the Apify API (e.g., POST to https://api.apify.com/v2/acts/{author~actor}/runs?token=...) to start an Apify actor (which executes remote scraping code) and later downloads results from https://api.apify.com/v2/datasets/{datasetId}/items?token=..., and these endpoints are required for the skill to function, so it triggers remote code execution on Apify.