Security audit

Scalping

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed trading-strategy template with financial risk warnings, not a skill that installs code, persists, or secretly accesses data.

Treat this as a risky trading template, not a recommendation. Backtest and paper-trade before any live use, review the futures and cross-margin settings carefully, and correct the minor time-stop comment if precision matters.

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 (1)

Intent-Code Divergence

Low

Confidence: 98% confidence
Finding: The inline comment states 'Time stop at 12 minutes (~3 bars on 5m),' but three 5-minute bars would be about 15 minutes. The code enforces 12 * 60 seconds, so the documentation actively misstates the implemented timing behavior.

Static analysis

No suspicious patterns detected.