ClawHub
Back to skill

Security audit

Hello World

Security checks for vulnerabilities and agentic risk

Overview

This is a simple greeting skill with no code execution, data access, persistence, or privileged behavior.

Installing this skill should be low risk. Expect it to take over simple hello or greeting requests and add a localized greeting, current date/time, and emoji; review it only if you prefer greetings to remain handled by the default assistant behavior.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
93% confidence
Finding
The trigger condition 'When the user asks you to say hello or greet someone' is broad and can match many ordinary conversational requests, causing the skill to activate unintentionally. Overbroad activation is dangerous because it can hijack normal assistant behavior, create confusing responses, and increase the chance that unrelated user inputs are routed through this skill instead of safer default handling.

Static analysis

No suspicious patterns detected.