ClawHub
Back to skill

Security audit

Backtesting Frameworks

Security checks for vulnerabilities and agentic risk

Overview

This skill is an educational backtesting guide with no hidden execution, data access, persistence, or account-control behavior.

Review and test the example backtester before relying on its metrics for financial decisions, especially the equity calculation for open positions. Installing the skill does not appear to grant special access or run code automatically.

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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This is a real logic flaw: the backtester builds the price map using the DataFrame index name (or a default string) rather than the actual traded symbol, so Portfolio.get_equity will usually fail to match open positions to prices. That causes equity, returns, and downstream risk metrics to be understated or wrong, which can mislead users into trusting invalid backtest results and deploying unsafe trading strategies.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The display name and description are written only in Chinese, which can impose a language preference on users without any opt-in or indication that the skill is intended solely for a Chinese-speaking or China-specific audience. Under the stated policy, a forced language/locale in natural-language metadata is a policy concern unless the constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.