gmaps-leads

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly fetches and ingests untrusted public web content — e.g., scripts/extract_website_contacts.py's fetch_page() pulls business main pages and contact pages and its search_for_contacts() scrapes DuckDuckGo HTML, and scripts/scrape_google_maps.py retrieves Google Maps listings via Apify — then passes that content into Claude for extraction which directly influences enrichment results and downstream actions like Google Sheet writes.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill fetches arbitrary external web pages at runtime (via fetch_page) — including DuckDuckGo HTML search results at https://html.duckduckgo.com/html/?q=... and the target business websites — and injects that fetched content directly into the Claude prompt for extraction, so remote content can control the model input and enable prompt-injection risks.