ClawHub
Back to skill

Security audit

Crypto Trading Decision Framework

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed crypto trading framework with no code execution or persistence, but users should treat its outputs as high-risk informational trading analysis, not financial advice.

Install only if you want the agent to provide structured crypto trade planning. Do not treat its recommendations as financial advice or let them drive live trades without independent review, current market data, and explicit human approval.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
---

## Gate 2 — Entry Checklist (must answer all YES)

1. ☐ Backtest sample size n ≥ 20 trades
2. ☐ Profit factor (PF) ≥ 1.3 in out-of-sample test window (not just training)
Confidence
80% confidence
Finding
Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger conditions are broad enough to activate on many generic trading conversations, which can cause the skill to steer users into a prescriptive trading framework when they did not explicitly request it. In a finance context, over-invocation increases the chance of unsolicited real-money trading guidance and may bypass safer, narrower handling for general educational discussions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill provides a concrete template for real-money trade recommendations, including entries, stops, targets, sizing, and escalation decisions, without a prominent upfront financial-risk warning or clear statement that outputs are informational rather than financial advice. In a high-volatility crypto setting, users may over-rely on the format's apparent precision and execute harmful trades with real capital.

Static analysis

No suspicious patterns detected.