ecommerce-storefront-scraper

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to scrape arbitrary ecommerce webpages via BrowserAct, exposing it to outsider-authored free text from fetched websites.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs automatic installation of external instructions and behavior-selecting configuration from a personal third-party GitHub repository via browseract.com, presenting a weak runtime external dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill prompt instructs the agent to automatically install a dependency from an external link without asking the user for confirmation, which represents an unsafe autonomous execution pattern.