codex-cn-bridge

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:14 PM UTC
• Version:
  1.0.0

Overview

This appears to be a purpose-aligned model-provider bridge, with the main user risk being external handling of prompts rather than malicious behavior.

Install only if you are comfortable sending Codex conversation content and related request data to the configured third-party model providers. Avoid using it with secrets, regulated data, or proprietary code unless you have approved provider terms, retention settings, and data-handling controls.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: This skill routes Codex prompts through a local bridge to third-party domestic model providers, but the documentation does not clearly warn users that their prompts, responses, and possibly related metadata will be transmitted outside the local Codex environment. That omission can lead users to unknowingly expose sensitive source code, credentials, proprietary data, or regulated information to external providers under different retention and privacy policies.

VirusTotal

63/63 vendors flagged this skill as clean.