ClawHub
Back to skill

Security audit

缠论买点扫描闭环

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed stock-scanning and watchlist/report workflow, with financial-risk caveats but no evidence of hidden exfiltration, persistence, or destructive behavior.

Install only if you are comfortable letting the agent use authenticated market/watchlist connectors, update Tencent watchlist groups, and produce trading-action reports. Treat the report as decision support, verify market data and formulas before placing any real orders, and review the generated HTML before acting on sell or clear-position recommendations.

SkillSpector

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
88% confidence
Finding
The skill instructs the agent to modify script variables and generate an HTML report, which implies file-writing behavior, but the skill declares no corresponding permissions. This mismatch is dangerous because an agent or runtime may perform filesystem writes without explicit user-visible authorization boundaries, increasing the risk of unintended overwrites or unauthorized artifact creation.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
This is a real logic/integrity flaw: the HTML report tells users one risk-control policy ('跌破5日线止盈，跌破10日线止损'), but the implemented triggers are materially different ('MA5 × 1.10' take-profit and 'MA10 × 0.97' effective stop-loss). In a trading automation/decision-support skill, this mismatch can cause users to place or trust orders under false assumptions, leading to unmanaged downside or missed exits.

Static analysis

No suspicious patterns detected.