ClawHub

MemeCoin分析师

Security checks across malware telemetry and agentic risk

Overview

This crypto-analysis skill is mostly documentation-only, but it exposes a live-looking payment API key and leaves billing/credential ownership unclear.

Review before installing. Ask the publisher to remove and rotate the exposed SkillPay key, clarify who pays for each call, declare required credentials, and provide a verified endpoint or source code before relying on the service. Treat any crypto output as informational only, not investment advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Intent-Code Divergence

High
Confidence
99% confidence
Finding
The documentation includes a concrete, live-looking API key directly in the skill file, which is a credential exposure. This is especially risky because the same document later indicates secrets should be passed via environment variables, strongly suggesting this value is meant to be sensitive and could be abused for unauthorized API access, billing fraud, or service impersonation.

Missing User Warnings

High
Confidence
99% confidence
Finding
A live-looking secret is exposed in plaintext with no warning that it is sensitive, increasing the likelihood that users copy, reuse, or redistribute it insecurely. In a paid skill context using SkillPay.me, exploitation could lead to unauthorized consumption of a billable service, account abuse, or financial loss for the operator.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal