google-shopping-product-offer-scraper

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

• Third-party content exposure detected (low risk: 0.10). The agent navigates to arbitrary web pages and search queries via browser extraction to collect product offers.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to automatically download and install a runtime skill/CLI dependency from an external third-party URL (https://www.browseract.com/...), representing an unofficial operational dependency with weak/unknown provenance.