ClawHub
Back to skill

Security audit

Minimax Crypto Trading

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed crypto trading advisor, but it can produce direct trade instructions without a financial-risk warning and may activate from broad market terms.

Review this carefully before installing. It does not execute trades or access accounts, but it can give direct crypto trade instructions that may lead to real financial loss. Use it only as informational analysis, require explicit user intent before invoking it, and do not treat its EXECUTE outputs as professional financial advice.

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
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill is designed to emit concrete execution instructions like EXECUTE_LONG / EXECUTE_SHORT with entry, stop, and targets, but it provides no warning that this is financial decision support and may lead to real monetary loss. Because the skill positions itself as a 'professional-grade' decision agent and restricts outputs to decisive trade actions, users may over-trust the output as authoritative investment advice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger terms are broad, common market words such as 'crypto', 'trading', 'BTC', 'ETH', and 'market analysis', which can cause the skill to activate during ordinary discussion rather than an explicit request for this high-stakes trading workflow. In the context of a skill that produces actionable trade decisions, accidental invocation increases the chance of unsolicited financial guidance and inappropriate execution-style outputs.

Content

No source excerpt is available for this finding.