ClawHub
Back to skill

Security audit

A股数据SKILL

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent A-share market-data lookup tool, with normal dependency and external API risks but no evidence of credential access, destructive behavior, or hidden control.

Install only if you are comfortable with stock queries being sent to third-party market-data APIs and with unpinned Python data packages. Treat the single-category financial commands as generic financial indicators unless the skill is fixed, and avoid using this output as the sole basis for investment decisions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The single-metric financial commands (`--profit`, `--growth`, `--balance`, `--cashflow`, `--dupont`) all route to `_financial_single_from_akshare`, which ignores `func_name` and returns the same generic `stock_financial_analysis_indicator` dataset for every request. In a finance skill, this is dangerous because users may make decisions believing they received a specific analysis category when the output is actually unrelated or incomplete, creating integrity and trust risks rather than classic code-execution risk.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.