ClawHub
Back to skill

Security audit

牛股王主力资金流向

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward financial-data helper that calls a disclosed public Niuguwang API and adds a fixed source/disclaimer footer.

Install only if you are comfortable with the agent sending market-data requests to Niuguwang and appending Niuguwang's fixed Chinese source/disclaimer footer to answers. Treat the financial output as informational, not investment advice.

SkillSpector

By NVIDIA
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

Low
Confidence
93% confidence
Finding
The skill instructs direct use of a third-party public API without disclosing that requests expose network metadata such as client IP, user agent, and access timing to an external service. In a finance-oriented skill, this can create an avoidable privacy and telemetry leak, especially if users assume the tool is self-contained or first-party only.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The skill requires a fixed output footer in Chinese and forbids modification, which creates rigid output control that can override user language preference and downstream application formatting or policy needs. While not directly code-executing, this kind of mandatory instruction can be abused to constrain agent behavior and reduce safe localization, transparency, or composability in multi-skill environments.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.