web-performance-audit

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to call navigate_page(url: "") and to list/get network requests (e.g., list_network_requests, get_network_request) to load and analyze arbitrary target URLs, meaning it fetches and interprets open/public third-party site content as part of its decision-making.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill asks the user to add an MCP config that runs "npx -y chrome-devtools-mcp@latest", which at runtime fetches and executes remote npm package code that the skill relies on, so it is a required external dependency that executes remote code.