One API key for Chinese AI models. Route to Qwen, Deepseek

• Outcome: Pass
• Latest audit: May 28, 2026, 10:48 AM
• Version:
  1.0.1

Overview

This is a straightforward AIsa LLM gateway client that sends user-chosen chat requests to the documented API endpoint and shows no hidden execution, persistence, or unrelated data access.

Install only if you intend to use AIsa/api.aisa.one as a third-party LLM gateway. Use a dedicated API key, monitor costs and quota, avoid hardcoding or pasting the key into chats or logs, and do not send secrets, regulated data, proprietary code, or private image URLs unless you accept the provider's data-handling terms.

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: 94% confidence
• Finding: The documentation instructs users to send prompts, messages, and potentially sensitive content to a third-party API, but it does not warn that this data leaves the local environment and may be retained or processed by the provider. Users may unknowingly submit secrets, internal code, personal data, or regulated content to an external service.

Missing User Warnings

Low

• Confidence: 90% confidence
• Finding: The skill references use of the AISA_API_KEY environment variable but does not warn users to protect the credential from logs, screenshots, shell history, or accidental inclusion in prompts and code samples. While the document does not directly exfiltrate the key, weak credential-handling guidance increases the chance of user-caused secret exposure.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The CLI sends user-provided prompts and optional system/messages content to a third-party API, but the interface does not clearly warn users that their input will leave the local environment. In a skill context, users may paste secrets, proprietary code, or sensitive operational context, making undisclosed transmission a real privacy and data-handling risk.

VirusTotal

62/62 vendors flagged this skill as clean.