Chines LLM Models (MiniMax 2.5,Kimi 2.5, Qwen, Doubao, DeepSeek) with one key

• Outcome: Pass
• Latest audit: May 28, 2026, 11:31 AM
• Version:
  1.0.0

Overview

This is a documentation-only skill for configuring AIsa as an OpenClaw model provider, with credential-handling cautions but no hidden or malicious behavior found.

Install only if you intend to route OpenClaw model traffic through AIsa. Prefer interactive onboarding or a secure secret store, avoid putting real API keys directly in command history or logs, verify current pricing and privacy/ZDR terms yourself, and remember that setting AIsa as the default model may send future prompts to AIsa and incur usage charges.

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 (3)

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The documentation explicitly tells users to pass the API key as a command-line argument, which can expose the secret through shell history, process listings, terminal logging, CI logs, or audit tooling. Because this skill is specifically about configuring a production API provider, the likelihood of real credential exposure is materially higher than in a toy example.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The guide instructs users to place the API key in an environment variable without any warning about secret-handling risks. While environment variables are commonly used, they can be exposed through shell history if entered unsafely, inherited by child processes, logged by tooling, or leaked in debugging and crash output; in a provider-configuration skill, this is a real credential hygiene issue because the secret grants access to paid external AI services.

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: Passing the API key directly on the command line is dangerous because command-line arguments are often recorded in shell history and may be visible to other local users via process inspection tools. In this skill's context, the key is a bearer credential for a third-party API gateway, so disclosure can lead to unauthorized usage, billing abuse, and potential access to account-scoped model activity.

VirusTotal

64/64 vendors flagged this skill as clean.