Is aisadocs/openclaw-aisa-llm-router safe?

https://github.com/openclaw/skills/tree/main/skills/aisadocs/openclaw-aisa-llm-router

90
SAFE

This skill provides a legitimate unified gateway to access 70+ LLM models through a single API. The Python client script is clean and makes expected HTTP requests to the documented service endpoint.

Category Scores

Prompt Injection 95/100 · 30%
Data Exfiltration 85/100 · 25%
Code Execution 80/100 · 20%
Clone Behavior 95/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 90/100 · 5%

Findings (3)

INFO External API Dependency -15 ▶

The skill makes HTTP requests to api.aisa.one to route LLM requests. This is the expected behavior for this type of service.

LOW Executable Python Script -20 ▶

Contains a Python script that functions as an HTTP client for the LLM routing service. Code review shows no malicious patterns.

INFO API Key Requirement -10 ▶

Skill requires users to provide AISA_API_KEY environment variable for authentication with the external service.