ClawHub

Quote.Trade Operator — AI-Native Dark Pool DEX for Trading Bots and Autonomous Agents

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Quote.Trade guidance helper, with some trading-safety caveats but no hidden execution, persistence, or exfiltration behavior in the artifacts.

Install this only if you want Quote.Trade integration help. Keep it in quote-only or paper mode unless you deliberately approve a live action, never share private keys or API secrets in chat, and review any optional external bot repository in a sandbox before running it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The skill’s narrative says credential operations should require explicit user approval and that the default mode is safe quote-only testing, but the machine-readable trade proposal sets "approvalRequired": false. In an agentic context, structured templates are often consumed more authoritatively than prose, so this contradiction can lead downstream agents or orchestration code to place trades without an explicit user consent gate.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The explicit value "approvalRequired": false permits an autonomous consumer of this JSON template to interpret trade proposals as pre-approved for execution. Because this skill is designed for bot/agent workflows around a trading platform, removing the approval gate materially increases the risk of unauthorized or unintended order placement and resulting financial loss.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal