ClawHub
Back to skill

Security audit

Hello World

Security checks across malware telemetry and agentic risk

Overview

This is a simple hello-world greeting plugin with no sensitive access; its main drawback is that it may trigger on ordinary greetings.

Install this only if you want a demo greeting tool. Be aware that greetings like `hi` may invoke the plugin automatically, but the reviewed artifacts do not show sensitive permissions or hidden behavior.

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 skill metadata describes activation for generic greetings and plugin tests, which overlaps heavily with common conversation. In agent environments that auto-select skills based on natural language, this can cause the skill to trigger unintentionally and intercept ordinary user messages, creating misrouting and unnecessary tool invocation risk.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The usage section defines broad triggers like "hello" and "hi" without strong activation boundaries, making accidental invocation likely during routine conversation. While the tool appears low risk, ambiguous routing can still degrade agent behavior, override better-matched skills, and normalize unsafe trigger design patterns.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.