Back to skill

Security audit

030复盘

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language A-share trading review checklist with no code execution or hidden system access, but users should treat its trading rules as risky educational guidance rather than financial advice.

Install only if you want a Chinese-language framework for manually reviewing A-share short-term trading conditions. Do not treat its position sizes, buy signals, sell rules, or liquidation triggers as personalized investment advice; verify data independently and consider your own risk tolerance or a licensed professional 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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill gives concrete trading rules, position-sizing guidance, liquidation triggers, and next-day action plans, but does not warn users that the content is not financial advice and can cause real financial loss. Because the framework is prescriptive and framed as actionable decision support, users may rely on it as investment advice without understanding the risks, limitations, or suitability constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file presents all instructions, labels, and templates exclusively in Chinese, and there is no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.