ClawHub
Back to skill

Security audit

aigate

Security checks across malware telemetry and agentic risk

Overview

The skill transparently documents a powerful self-hosted AI gateway with broad optional capabilities, but it does not hide them or force them on by default.

Install only if you intend to run a high-authority local AI gateway. Keep it private, use a strong AIGATE_TOKEN, split per-service tokens for risky tools, enable only the services you need, and avoid giving the master token to untrusted agents or prompts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
**This is a very high-capability, very high-blast-radius stack. Treat the endpoint and its token like root on the host.** A single `AIGATE_TOKEN` bearer can, depending on what's enabled:

- Hold API keys/credentials for many cloud model providers (Groq, Cerebras, OpenRouter, HuggingFace, Mistral, Cohere, Anthropic, OpenAI) plus flat-rate agent backends (Claude Code OAuth/API key, z.ai).
- Execute arbitrary code — two full agentic coding agents (claudebox, pibox-zai) with shell + file access, plus sandboxed multi-language execution (piston).
- Drive a real browser (stealth Camoufox cluster) that can log into sites, fill forms, and act as the user across the open web.
- Send email and Telegram messages on the user's behalf (mailbox, Telethon) — mailbox additionally holds plaintext IMAP/SMTP credentials in its YAML config.
- Read/write S3-compatible object storage with a public-read bucket.
Confidence
97% confidence
Finding
Execute arbitrary code

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.