ClawHub
Back to skill

Security audit

MoneybigA

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed stock-analysis skill that uses public web data and does not request credentials or trading authority, but its buy/sell outputs should be treated as informational only.

Install only if you want an assistant to perform broad stock-market analysis when finance terms or tickers are discussed. Do not treat its buy/sell signals, targets, or stop-loss levels as personalized financial advice, and verify market data and conclusions independently before making investment decisions.

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
91% confidence
Finding
The skill advertises a very large set of trigger phrases spanning generic investment, finance, and market-analysis terms in both Chinese and English. This can cause unintended activation in ordinary conversation, increasing the chance the skill runs when the user did not explicitly request it and potentially causing unnecessary web access, misleading financial guidance, or context hijacking.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation rules in the '何时触发' section are broad and based on common market-related topics like stock codes, technical-analysis terms, or financial-report discussion. In a chat environment, this makes the skill prone to over-triggering on benign discussion, which can unexpectedly steer the conversation, initiate data collection, or surface high-confidence investment signals without a deliberate user request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.