ClawHub
Back to skill

Security audit

binance-square-author

Security checks across malware telemetry and agentic risk

Overview

This is a crypto content-writing skill with no executable behavior, but its sample posts include specific trading advice users should review before publishing.

Install only if you want a crypto-content drafting assistant. Before publishing, verify all market data independently, remove specific buy/sell/add-position calls or guaranteed-return style language, include clear risk and non-investment-advice disclaimers, and do not connect this workflow to exchange, wallet, or auto-posting permissions without a separate review.

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 (1)

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The skill’s compliance section says not to recommend specific coins, yet the document elsewhere gives concrete asset-specific trading actions such as buying, holding, and adding to BTC or ETH positions. This inconsistency can cause the agent to produce regulated or policy-violating financial advice, especially because the skill is framed as authoritative content guidance and includes actionable price levels.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.