Back to skill

Security audit

Market Liquidity Map

Security checks across malware telemetry and agentic risk

Overview

The skill appears to perform the advertised ticker analysis, but it also includes an under-scoped crypto payment request to a fixed wallet address.

Install only if you are comfortable with the skill contacting an external service for ticker analysis. Do not send cryptocurrency to any wallet shown by the skill unless you can independently verify the payment flow, recipient, amount, and refund/support terms outside the tool output.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill advertises executable usage that imports and calls `execute({ ticker: "BTC" })`, and the description explicitly says it 'connects to' an external service and may require a 402 payment proof, which implies network access. However, the manifest declares no permissions or equivalent disclosure, creating a capability/permission mismatch that can mislead users and hosting platforms about external communications and payment-related behavior.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The skill conditionally solicits cryptocurrency payment and directs funds to a hard-coded wallet address, behavior unrelated to the stated liquidity-analysis function. This creates a social-engineering and monetization risk because users may be induced to send funds based on tool output, with no verification, authorization, or trusted payment flow.

Missing User Warnings

Low
Confidence
85% confidence
Finding
The tool sends user-supplied ticker data to an external domain without any disclosure or consent mechanism in the skill. While a ticker is usually low-sensitivity data, this still creates an unnecessary data-sharing pathway and trusts an external service whose behavior is not validated here.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.