cmux

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly opens and automates arbitrary web pages using cmux's built-in browser (see SKILL.md and references/browser.md: e.g., "cmux --json browser open " plus snapshot/get text/get html/eval/click/fill commands), so the agent fetches untrusted third-party content and reads/acts on it, enabling indirect prompt injection.