ClawHub
Back to skill

Security audit

Trading Brain

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed trading playbook, but it broadly steers agents toward aggressive financial decisions and local trading-account data without clear user-confirmation boundaries.

Review this before installing if the agent may access brokerage files or make trade recommendations. Treat it as a high-risk financial decision aid: keep brokerage credentials scoped, require explicit confirmation before any order or account-changing action, and verify market data and risk limits independently.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill instructs invocation at the start of nearly any trading analysis or investment research session, making it a persistent behavioral override rather than a narrowly scoped helper. This broad trigger surface can bias many downstream decisions, encourage over-reliance on the embedded strategy, and cause the agent to apply aggressive trading guidance in contexts where it may be inappropriate or insufficiently verified.