ClawHub
Back to skill

Security audit

A股个股深度投资报告生成器

Security checks across malware telemetry and agentic risk

Overview

This skill coherently generates A-share investment report markdown files using web research, with no hidden installation, credential access, or unsafe persistence found.

Before installing, be aware that mentioning company names in a report-generation context may lead the agent to perform web searches and create one or more markdown files. For batch use, specify the target folder and ask the agent to confirm filenames before writing. Treat the generated investment ratings, target prices, and trading plans as research drafts, not financial advice.

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 condition is overly permissive because it says a company name alone is enough to activate the skill, which increases the chance of accidental invocation when a user merely mentions a stock or company in passing. In this skill, activation can lead to web searches and file generation, so broad triggering creates unnecessary side effects and weakens user intent verification.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs writing markdown files into the workspace by default without a clear user-facing warning or confirmation about where files will be created. Because this skill supports batch generation, an unintended trigger or misunderstood request could create multiple files and clutter or overwrite expected workspace contents.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.