use-my-browser

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md and references (e.g., references/tool-matrix.md and browser-recipes.md) explicitly instruct the agent to use public-web tools like web.search_query, web.open, raw fetches, and to visit social/dynamic sites (examples mention X.com and public pages) so the agent will fetch and interpret untrusted, user-generated third‑party content which can change tool routing and follow-on actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime configuration and prerequisites instruct running the Chrome DevTools MCP package (e.g., via "bunx chrome-devtools-mcp@latest" / "npx chrome-devtools-mcp@latest"), which fetches and executes remote code and is required for the live-browser functionality (see https://github.com/ChromeDevTools/chrome-devtools-mcp).