ClawHub
Back to skill

Security audit

Backtester

Security checks for vulnerabilities and agentic risk

Overview

This skill looks like a trading backtester, but its script prints fixed favorable results instead of doing real analysis.

Install only if you treat it as a placeholder or demo. Do not rely on its reported returns, Sharpe ratio, drawdown, trade counts, or outperforming conclusion for trading or investing decisions unless the publisher replaces the hard-coded output with real data loading and calculations.

SkillSpector

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)

Description-Behavior Mismatch

High
Confidence
98% confidence
Finding
The skill advertises a professional backtesting framework but the implementation only prints fixed, favorable performance metrics and performs no historical-data analysis. This is dangerous because users may rely on fabricated results to make trading or risk decisions, creating a deception/integrity failure even though there is no direct code-execution exploit.

Static analysis

No suspicious patterns detected.