ClawHub

A Stock Analysis Lite

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only A-share stock report generator that uses public financial data sources and does not request private access or privileged actions.

Install this if you want automatic Chinese A-share research reports from public web data. Be aware it may trigger on simple stock-code mentions and perform multiple external finance-site lookups; verify financial figures independently and do not treat the generated report as investment 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
90% confidence
Finding
The README states that entering a stock code is sufficient to trigger analysis, but it does not clearly bound when the skill should activate or what user intent must be present. In an agent environment, broad trigger rules can cause unintended invocation on incidental 6-digit numbers or vague finance-related prompts, leading to unnecessary external data access, incorrect task routing, or surprising behavior.

Vague Triggers

High
Confidence
96% confidence
Finding
The skill is configured to trigger on very broad stock-related phrases such as any 6-digit A-share code, stock name, or generic requests like '看看这只票', which can easily match ordinary conversation and cause unintended invocation. This creates routing hijack risk: the agent may invoke this skill when the user did not actually want a full report workflow, leading to unnecessary data collection, wrong tool selection, and reduced reliability of the overall system.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal