ClawHub
Back to skill

Security audit

options-strategies

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only options strategy reference with financial-risk caveats to consider, but it does not contain code, persistence, credential access, or hidden agent behavior.

Review this as educational options content, not personalized financial advice. Options can involve total loss, assignment, margin exposure, and in some strategies unlimited loss; users should apply their own risk tolerance, account limits, and professional guidance before acting on any strategy.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

High
Confidence
96% confidence
Finding
The skill gives concrete trading setups, strategy-selection logic, DTE guidance, and premium-selling recommendations without any warning that this is educational content rather than personalized financial advice. Because options strategies can involve substantial or even unlimited loss, omission of risk disclosures and suitability checks can materially increase user harm if guidance is followed as actionable advice.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger description is broad enough to match many ordinary requests about options, which can cause the skill to activate in situations where the user did not intend to receive structured trading guidance. In a financial domain, unintended invocation increases the chance of overconfident, context-poor, or unsuitable strategy suggestions being surfaced without proper qualification.

Static analysis

No suspicious patterns detected.