lead-enrichment

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly submits arbitrary business websites to the Apify Contact Details Scraper (actor QAKrfXwAcbmcWYnSo) as shown in SKILL.md and scripts/lead-enrichment.js, then reads the scraped items from the actor dataset (run.defaultDatasetId) and uses extracted emails/phones/social handles to update the business_leads table, so untrusted third-party page content is ingested and can materially influence downstream behavior.

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

• Potentially malicious external URL detected (high risk: 0.70). The script calls the Apify actor ID QAKrfXwAcbmcWYnSo at runtime via the Apify API (e.g., https://api.apify.com/actors/QAKrfXwAcbmcWYnSo), which executes remote scraping code and is a required dependency (APIFY_API_KEY), so this external actor runs code outside the agent's environment.