ClawHub
Back to skill

Security audit

AI智能交易Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese trading-analysis skill with financial-risk caveats and no evidence of hidden execution, data access, persistence, or account actions.

Use this only as an educational trading-analysis aid. Confirm you understand the Chinese output and independently verify prices, risks, position sizes, and legal or tax implications before making any financial decision.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list contains broad phrases such as ‘市场分析’, ‘风险管理’, and ‘TradingView’ that can appear in many ordinary finance or charting conversations, increasing the chance of unintended skill activation. In a trading context, accidental invocation is more sensitive than usual because the skill produces trading signals and position-sizing guidance, which could steer users toward financial decisions they did not explicitly request from this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Forcing Chinese output without user choice can create usability and comprehension failures for non-Chinese-speaking users. In this skill’s domain, misunderstanding trading parameters such as entry, stop-loss, or position size can have real financial consequences, so a language restriction is more operationally risky than in low-stakes content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.