ClawHub
Back to skill

Security audit

Gate Exchange Dual Investment

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Gate dual-investment helper that can place real orders only after confirmation, but users should treat its financial permissions carefully.

Install only if you intend to connect a trusted Gate MCP server to your Gate account. Use a dedicated least-privilege API key, verify every amount, target price, APY, and settlement scenario before confirming an order, and double-check minimum investment requirements in the Gate app or website if the skill gives conflicting guidance.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill’s error-handling section says to display the API error message returned by the service, while the safety rules explicitly prohibit exposing raw error traces. API error bodies often contain backend details, identifiers, validation internals, or environment-specific information that can leak operational context to users and aid abuse or reconnaissance.

Intent-Code Divergence

Medium
Confidence
89% confidence
Finding
The documentation gives contradictory guidance about whether minimum investment amounts are available via API: Scenario 3 says they are not available, while later scenarios instruct the agent to use `min_amount` for eligibility and minimum-purchase checks. This inconsistency can cause the agent to provide incorrect eligibility advice or fabricate unsupported values, leading users to place unsuitable orders or receive misleading financial guidance.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.