cmux

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill exposes the agent to untrusted third‑party content because its core CLI includes browser automation commands (e.g., "cmux browser open/goto", "browser get <html|text>", "browser eval", and "snapshot") described in SKILL.md and references/cli-reference.md that navigate to arbitrary URLs and read/execute page content which can influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 09:38 PM