ClawHub
Back to skill

Security audit

候茶商店

Security checks across malware telemetry and agentic risk

Overview

This is a transparent tea-shopping skill, but it can steer an agent into real USDC payment flows without a clear final confirmation step.

Install only if you want an agent to query hou-tea.com and help prepare crypto tea purchases. Before enabling any wallet or ordering credentials, require a separate final confirmation showing the product, quantity, total USDC amount, Base network, recipient address, and that real funds may be spent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation trigger is broad enough that ordinary mentions of tea or related words can automatically invoke a commerce-capable skill. In context, this is more dangerous than a benign informational skill because the skill can browse products and initiate purchase flows, increasing the chance of unintended commercial actions or steering users into a transactional workflow without clear intent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill provides detailed real-payment instructions for x402/USDC purchases but does not require a prominent user-facing warning or explicit confirmation before initiating a transaction. Because this skill is directly connected to financial transfer mechanics on Base, unclear transactional disclosure could cause accidental purchases, wallet prompts, or irreversible crypto payments.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.