ClawHub
Back to skill

Security audit

A股资金流向分析

Security checks across malware telemetry and agentic risk

Overview

This is a text-only A-share stock analysis skill with financial-reliance risks but no code, credential access, trading execution, or hidden behavior.

Install only if you want A-share capital-flow and position-analysis prompts. Treat outputs as educational analysis, verify market data and assumptions independently, and avoid relying on the skill as personalized investment advice or enabling recurring reports unless you deliberately want them.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly offers trading decisions, position diagnostics, and buy/sell strategy guidance, but it does not include any disclaimer that the output is informational only, may be wrong, or should not be treated as personalized financial advice. In the context of scheduled automated briefs and action-oriented recommendations, this increases the chance that users rely on the model for real financial decisions and suffer losses.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes very broad terms such as "股票" and "交易", which are common words likely to appear in many unrelated conversations about finance or markets. This can cause unintended activation of the skill, exposing users to investment-oriented outputs when they did not explicitly request this capability and increasing the chance of prompt-routing abuse or inappropriate execution context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.