primevideo

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

• Third-party content exposure detected (low risk: 0.10). The agent reads web pages and search results from primevideo.com via search and page-reading tools, which constitutes fetching external web content at runtime.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill configures a remote Model Context Protocol (MCP) server at unbrowse.ai, which acts as an operational dependency supplying tools and behavior-selecting configuration during runtime. Because unbrowse.ai is an arbitrary third-party platform with unknown publisher verification, this dependency falls under the weak/unknown tier.