ClawHub
Back to skill

Security audit

A-Share Stock Data API

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a stock-data API helper, but its bundled script silently uses an undisclosed default token that differs from the documented trial token.

Review this before installing. The API access itself is coherent with a stock-data skill, but you should avoid relying on the bundled default token, prefer supplying your own key through a header where possible, and treat the documented service as a third-party data provider that will receive your query parameters.

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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding
The skill description narrows the purpose to A-share quote/indicator/flow/finance queries, but the documentation also includes broader endpoints and a hardcoded default token for a third-party service. This mismatch reduces transparency, can bypass informed consent about what remote resources are contacted, and normalizes embedded credentials that may be abused or rate-limit-shared across users.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
Placing API tokens in URL query parameters is dangerous because URLs are commonly logged by servers, proxies, browser history, analytics systems, and error telemetry. The skill not only permits this pattern but promotes a reusable trial token in example requests, increasing the likelihood of credential leakage and unauthorized reuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.