ClawHub
Back to skill

Security audit

AI Trading Strategy Backtester

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed trading-strategy backtesting guide with documentation quality issues, but no hidden execution, persistence, credential use, or exfiltration behavior was found.

Install only if you want a research-oriented trading backtesting assistant. Review generated strategies carefully, verify market assumptions and data quality yourself, and do not treat illustrative performance numbers as financial advice.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (2)

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The skill switches into Chinese for major sections such as the market/regulatory context and later examples, while other sections remain in English. Because the file does not state that the skill is China-region-only or let the user choose a preferred language, this can violate language/locale expectations for users who did not opt into bilingual or Chinese output.

Intent-Code Divergence

Low
Confidence
97% confidence
Finding
The example request explicitly asks for a momentum strategy for the A-share market, but the same example includes US tickers and the output labels the market as 'US Equity (4 stocks)'. This is not merely incomplete documentation; it actively presents a mismatched example that contradicts the requested market context and could mislead users about what the skill is actually doing.

Static analysis

No suspicious patterns detected.