ClawHub
Back to skill

Security audit

StockIndexMonitoringAI

Security checks across malware telemetry and agentic risk

Overview

This skill only returns a simple greeting, though its public listing name does not match the Hello World behavior.

Install this only if you want a simple Hello World greeting skill. Because the listing name suggests stock-index monitoring while the artifact only implements greetings, confirm the publisher and package identity before relying on it.

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The natural-language trigger examples are broad enough to overlap with ordinary conversational requests, which can cause the skill to activate when the user did not explicitly intend to invoke it. While the behavior here is low-risk because the skill only returns a greeting and performs no privileged actions, ambiguous triggering can still degrade user control and create unintended executions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal