ClawHub
Back to skill

Security audit

Quit Vaping

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple quit-vaping helper with disclosed local tracking and no executable code, network behavior, or hidden privilege requests.

Before installing, understand that this skill may keep local notes about your quit date, cravings, and progress. Its health timeline is motivational guidance, not medical care; consult a qualified professional for medical or urgent cessation support.

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)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
92% confidence
Finding
The trigger phrase 'stop vaping' begins with the generic built-in command word 'stop', which can create ambiguity between invoking this skill and issuing a global stop/cancel action. In voice or text-driven agent environments, this can cause command shadowing, unexpected invocation behavior, or failure of safety-relevant interruption controls.

Static analysis

No suspicious patterns detected.