ClawHub
Back to skill

Security audit

指数直通车指数信息查询

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent index-market data lookup tool that uses a disclosed API key, local helper scripts, and a scoped external data service.

Before installing, confirm you trust the Index Hub provider and are comfortable storing an API key locally at ~/.config/index-hub/api_key and sending index query requests to www.etf.com.cn. The installer may replace an existing index-query skill in the chosen skills directory, so use --skills-dir if you need a separate install location.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill documentation instructs use of environment variables, local files, network access, and shell execution via `scripts/api_client.py`, yet no explicit permissions are declared. This creates a transparency and sandboxing gap: a host may grant broader capabilities implicitly, and reviewers or users cannot easily assess what the skill needs before installation or execution.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/api_client.py:64