vp-chrome-profiles

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

• Third-party content exposure detected (high risk: 0.90). This skill launches Chrome to arbitrary URLs and instructs the agent to connect via Chrome DevTools MCP and "list pages" / "inspect page content" (see SKILL.md Workflow steps 2–4 and scripts/chrome-profilectl's launch/mcp-args/status/print_endpoint_info), meaning the agent will read untrusted public web page content that can influence its actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill emits and directs users to run an npx command ("npx -y chrome-devtools-mcp@latest --browser-url=http://127.0.0.1:") which, if executed at runtime, will fetch and run remote package code from the npm registry, meaning the skill relies on that externally fetched code to connect to MCP and it executes remote code.