Security audit
AI Trading Strategy Backtester
Security checks for vulnerabilities and agentic risk
Overview
The skill is a disclosed trading backtesting assistant that provides guidance and example code without trying to trade, read files, install software, or use credentials itself.
Before installing, treat this as a research and code-generation aid only. Do not provide live account details, credentials, private trading records, or internal strategy parameters; verify any generated backtest code, costs, market rules, and regulatory assumptions before using it with real capital.
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
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep