NYC

codex-skill

Warn

Audited by Snyk on Feb 16, 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: 1.00). The skill explicitly exposes and encourages use of sandbox-bypassing flags and a "danger-full-access" mode that grants network and system-level operations, writing outside the workspace, and executing commands without confirmation—directly enabling changes to the host system and sandbox bypasses.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 11:12 AM