ecommerce-price-comparison-research

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses a browser tool to visit external web pages and search results chosen by the user or agent, representing low-risk outsider-authored content ingestion.

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 from an arbitrary third-party URL (browseract.com), constituting an unverified external dependency.