ClawHub
Back to skill

Security audit

One API key for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward LLM gateway client, but anything you send through it goes to AIsa and routed model providers.

Install only if you trust AIsa and its routed model providers with the prompts, message history, image links, and metadata you choose to submit. Keep AISA_API_KEY protected, monitor usage and billing, and avoid sending secrets, private documents, internal image links, or regulated personal data unless your organization has approved that provider.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares required binaries and an API key in metadata and clearly instructs users to make outbound requests to a third-party service, yet it does not declare explicit permissions for environment access and network use. This creates a transparency and consent gap: an agent or user may invoke the skill without realizing it can read secrets and transmit prompts, images, and other content externally.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation shows sending user prompts and image URLs/base64 image data to api.aisa.one for processing, but it does not prominently warn that potentially sensitive text and images leave the local environment and are handled by a third party. In agent settings, this can lead to unintentional disclosure of confidential data, proprietary prompts, or personal images.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.