ClawHub
Back to skill

Security audit

Hello Agent World

Security checks for vulnerabilities and agentic risk

Overview

This is a simple greeting skill with no code execution, persistence, credential access, or data handling beyond producing a customized hello message.

Installing this skill should be low risk. Expect it to activate on ordinary greeting requests and add a date/time, emoji, personalization when provided, and a short statement about agent capabilities.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s invocation condition, "When the user asks you to say hello or greet someone, use this skill," is overly broad and matches very common conversational requests. This can cause the skill to activate unexpectedly during ordinary chat, increasing the chance of unnecessary skill execution, context leakage into the response, or interference with normal assistant behavior, even though the skill itself is low-risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.