google-shopping-sku-ean-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 public web pages via browser automation to collect product and offer data, exposing it to outsider-authored web content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches and installs remote content from an arbitrary third-party repository (https://github.com/browser-act/skills/tree/main), introducing an unverified external runtime dependency with weak provenance.