A股基本面筛选

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese-language A-share stock screening helper with no executable code or hidden system access.

Install this only if you want a Chinese-language A-share fundamental screening aid. Treat outputs as preliminary financial analysis, verify market data independently, and ask explicitly when you want broader investment context rather than this fixed screening checklist.

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
86% confidence
Finding
The trigger phrases are broad, everyday investing questions such as whether a stock is fundamentally good or risky, which can overlap with normal conversation and cause the skill to activate unexpectedly. In an investment context, unintended invocation can steer users into a narrow screening workflow without clear consent, increasing the chance of inappropriate financial guidance or overconfident recommendations.

Natural-Language Policy Violations

Medium
Confidence
68% confidence
Finding
The skill content is entirely in Chinese and does not indicate any language fallback or user-choice mechanism, which can make behavior opaque for users operating in other languages. While not directly a code-execution issue, this can impair informed consent and increase the risk that users misunderstand screening criteria or outputs in a sensitive financial-decision context.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal