codex-safe-sandbox-no-approval
Fail
Audited by Snyk on Jun 21, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.90). This script intentionally weakens security controls by setting approval_policy="never" and sandbox_mode="workspace-write" (disabling approvals and granting workspace write access), a deliberate security bypass that enables potential remote code execution, data exfiltration, and persistent compromise.
Issues (1)
E006
CRITICALMalicious code pattern detected in skill scripts.
Audit Metadata