Security audit

中国AI API统一网关

Security checks across malware telemetry and agentic risk

Overview

This is a coherent API gateway skill that forwards user requests to configured AI providers, with no evidence of hidden collection, persistence, or destructive behavior.

Install only if you are comfortable sending prompts and API requests to the listed third-party providers. Store real API keys in environment variables or a secret manager, avoid exposing the gateway publicly without authentication or firewall controls, and check each provider’s pricing, logging, retention, and quota policies before use.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The examples instruct users to send prompts and API credentials to third-party endpoints but do not clearly warn that user content will leave the local environment and be processed by external providers. In a gateway skill, this omission is more dangerous because the whole purpose is routing requests across multiple vendors, increasing data-sharing and compliance risk.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill tells users to obtain, copy, and use API keys without any guidance on secure storage, rotation, masking, or least-privilege handling. This increases the likelihood of credential leakage through source code, logs, screenshots, shell history, or shared configs, which could lead to account abuse and billing loss.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.