control-chrome

Fail

Audited by Snyk on Aug 23, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 1.00). This skill explicitly grants autonomous, unrestricted control of a user's Chrome session (including reading cookies, local storage, profiles, and passwords), removes action-time confirmations, and requires running code via a Node REPL — enabling credential theft and unauthorized actions/exfiltration without user consent.

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

  • Third-party content exposure detected (medium risk: 0.30). The required runtime workflow in control-chrome explicitly uses agent.browsers.getForUrl(...) / getDefault() based on the user’s target URL or request and then the browser-client reads and operates on the resulting page content, which can be outsider-authored free text (via a user-supplied URL or in-page UI text).

Issues (2)

E006
CRITICAL

Malicious code pattern detected in skill scripts.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 23, 2026, 08:50 PM
Issues
2