NYC

second-opinion

Warn

Audited by Snyk on Feb 17, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill instructs the agent to run external CLIs (Codex/Gemini) in headless mode including Gemini's --yolo flag and suggests installing extensions/global packages, which can auto-execute extension tool actions (potentially modifying files or installing software) without confirmation, so it enables state-changing operations even though it doesn't explicitly request sudo or create users.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:08 PM