Save upto 50% for model tokens: OpenAI GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with one single key
PassAudited by ClawScan on May 1, 2026.
Overview
This skill is a coherent LLM gateway client that uses an AISA API key to send user prompts and images to an external model-routing service.
This appears safe for its stated purpose. Before installing, make sure you are comfortable sending prompts and image inputs to AIsa's gateway, understand any downstream provider routing, and use an API key with appropriate limits.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Anyone using the skill can send requests that may consume credits or bill against the AISA account associated with the key.
The client reads an AISA API key and uses it as a bearer token for the gateway. This is expected for the skill's purpose, but it grants account/API usage authority.
self.api_key = api_key or os.environ.get("AISA_API_KEY") ... "Authorization": f"Bearer {self.api_key}"Use a scoped or low-limit AISA key if available, monitor usage, and avoid sharing the key in prompts or logs.
Prompts, uploaded/base64 image content, image URLs, and other request content may leave the local agent environment and be processed by AIsa and downstream model providers.
The skill sends chat, vision, and model-comparison requests to an external gateway that may route them to multiple model providers. This data flow is disclosed and purpose-aligned.
POST https://api.aisa.one/v1/chat/completions ... Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key.
Review the gateway's privacy, retention, and provider-routing terms before sending sensitive business, personal, or regulated data.