ClawHub
Back to skill

Security audit

Auto Trading Strategy

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only trading guide skill with financial-risk content but no code execution, persistence, credential access, or hidden behavior.

Install only if you want educational trading-strategy material. Do not treat its examples, whale-following advice, win-rate claims, or position-sizing formulas as personalized financial advice or as proof that the skill can execute real-time monitoring or backtesting.

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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The quick-start phrases are generic requests such as analyzing a market trend or reviewing a trading strategy, which can easily overlap with normal user intent and cause the skill to activate unexpectedly. In a finance/trading skill, unintended invocation is more concerning because it may steer users toward domain-specific guidance that affects financial decisions, even if the content itself is not overtly malicious.

Vague Triggers

Medium
Confidence
94% confidence
Finding
This promotional text advertises the skill broadly without defining when the skill should activate or what user intents it is meant to handle. In agent ecosystems, vague scope increases the chance of overbroad invocation or unintended triggering, which can cause the skill to influence unrelated financial conversations and provide risky trading guidance outside an appropriate context.

Static analysis

No suspicious patterns detected.