novel-assistant

Fail

Audited by Snyk on Aug 11, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 1.00). The package includes an internal "browser-cdp" skill that explicitly automates a Chrome CDP session to evaluate JS and extract auth tokens/cookies (and contains commands that can kill Chrome processes), which are clear capabilities for credential theft and covert data exfiltration and therefore present a high abuse risk.

Issues (1)

E006
CRITICAL

Malicious code pattern detected in skill scripts.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 11, 2026, 11:38 AM
Issues
1
Security Audit — snyk — novel-assistant