Back to skill

Security audit

A股量价关系验证

Security checks across malware telemetry and agentic risk

Overview

This is a text-only A-share volume-price analysis skill with no code or account access, but users should treat its trading conclusions as general education rather than financial advice.

Install only if you want general technical-analysis prompts for A-share market discussion. Do not treat the skill's buy, chase, or position-building language as personalized financial advice, and verify any trading decision with broader research, risk limits, and qualified guidance.

SkillSpector

By NVIDIA
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
Confidence
93% confidence
Finding
The trigger phrases are very broad everyday trading questions such as '能追吗' and '这是诱多还是真涨', which are likely to appear in normal market discussions and can cause unintended invocation. In a financial-analysis skill, accidental activation is risky because the skill provides directional trading guidance that users may act on without realizing a specialized skill has taken over the response.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill gives concrete trading recommendations like '可跟进', '不可追', '可考虑建仓', and '可果断跟进' without any warning that the content is educational, probabilistic, and not individualized financial advice. This is dangerous because users may treat simplified heuristic rules as actionable investment advice, increasing the chance of financial loss in a high-risk domain.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.