Back to skill

Security audit

AI智能交易Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language trading-analysis prompt skill with no code execution, persistence, account access, or hidden data handling.

Install only if you want Chinese-language trading analysis prompts. Treat outputs as educational analysis, not financial advice, and verify any trading signal, stop loss, take profit, or position-size calculation independently before acting.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list contains broad phrases such as '市场分析', '风险管理', and 'TradingView' that are common across many benign finance-related conversations. This can cause unintended invocation of the skill in contexts where the user did not request systematic trading analysis, increasing the chance of inappropriate activation and off-target responses in a sensitive financial domain.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill hardcodes Chinese-only output without indicating user choice, which can override the user's preferred language and reduce clarity or informed consent. In a trading-related skill, language mismatch can materially affect comprehension of risk, stop-loss, and position-sizing details, making misunderstandings more consequential than in casual contexts.

Content

No source excerpt is available for this finding.