Back to skill

Security audit

Bollinger Reverter 4h

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent trading-strategy skill, but users should treat it as high-risk financial guidance rather than a guaranteed or production-ready bot.

Before installing or using this skill, treat it as speculative trading guidance. Validate the strategy yourself, dry-run or paper-trade first, understand that futures can liquidate funds quickly, and do not rely on the quoted backtest as a guarantee of future results.

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
  • 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
91% confidence
Finding

The skill repeatedly states that the strategy depends on its minimal_roi ladder and documents the ladder as core behavior, but the provided reference config sets minimal_roi to {"0": 100.0}, which would disable normal ROI-taking if taken at face value. Although line L135 clarifies that strategy-level minimal_roi overrides config-level, the config snippet itself actively presents contradictory behavior to the documented trading logic.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill recommends deploying an automated futures strategy with isolated margin and concrete wallet sizing guidance, but does not include an explicit warning about real-money loss, liquidation, leverage/margin risk, or the limits of backtests. In this context, omission of risk disclosure can materially increase the chance that a user treats the strategy as production-ready and incurs financial loss.

Content

No source excerpt is available for this finding.