ClawHub
Back to skill

Security audit

yanji-kline-data

Security checks across malware telemetry and agentic risk

Overview

This skill is a small stock-quote helper with disclosed live Sina Finance access and demo-only moving-average estimates, but users should not treat its indicators as real historical K-line analysis.

Install only if you want a lightweight demo/teaching tool for Chinese stock quotes. Treat the moving averages as simulated estimates, not market-derived indicators, and avoid using the output for trading or formal financial decisions without a real historical data source.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation explicitly describes outbound access to Sina Finance (`hq.sinajs.cn`) but does not declare any corresponding permission, creating a transparency and policy-enforcement gap. Undeclared network access can bypass user or platform expectations, and if the script is executed in a broader agent environment it may enable unintended data exfiltration or unreviewed external communications.

Description-Behavior Mismatch

Medium
Confidence
97% confidence
Finding
The skill advertises K线/price-trend retrieval but only fetches a single real-time quote and then fabricates moving-average-like values from the current close price. In a financial-analysis context, presenting synthetic indicators as if they were market-derived data can mislead downstream users or agents into making incorrect investment or reporting decisions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.