ClawHub
Back to skill

Security audit

Crypto Price

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it claims: fetch public cryptocurrency market data and generate temporary chart images, without evidence of credential access, hidden persistence, exfiltration, or destructive behavior.

Install this if you are comfortable with a skill that runs a local Python script, contacts CoinGecko or Hyperliquid for public price data, and writes temporary cache/chart files in /tmp. For stricter environments, pin matplotlib and document the required network and /tmp file permissions explicitly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill directs execution of a Python script that uses network access and writes files under /tmp, but the skill metadata does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: a host may allow the skill assuming minimal capability while it can still reach external APIs and create local artifacts, increasing the risk of unexpected data access or side effects.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The README states the skill is automatically triggered for broad categories like token prices, crypto charts, and cryptocurrency market data without defining tighter invocation boundaries. In an agent system, overly broad auto-trigger conditions can cause the skill to activate on loosely related prompts, increasing the chance of unnecessary external API calls, unintended tool use, and context leakage to third-party services.

Unpinned Dependencies

Low
Category
Supply Chain
Content
matplotlib>=3.5.0
Confidence
89% confidence
Finding
matplotlib>=3.5.0

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.