ClawHub
Back to skill

Security audit

K线超短线选股

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed A-share stock-screening helper that fetches public market data and writes local reports, with no evidence of credential use, persistence, trading, or hidden behavior.

Install only if you are comfortable with the skill fetching public market data from Chinese finance sites and writing screening outputs in your current directory. Treat the reports as research aids, not investment advice, and review any future version carefully if it adds automated trading or brokerage/API account access.

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
95% confidence
Finding
The skill instructs execution of local scripts that perform network access and write output files such as candidates.json, kline_data.json, and HTML reports, but the skill declares no corresponding permissions. This creates a capability/permission mismatch that can bypass expected review or runtime controls, especially because the workflow is designed to fetch external market data and persist generated artifacts automatically.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.