ClawHub
Back to skill

Security audit

Quit Smoking

Security checks for vulnerabilities and agentic risk

Overview

This is a simple quit-smoking support skill that keeps local progress notes and does not include code, network access, or hidden behavior.

Before installing, understand that the skill may store quit-smoking progress locally for tracking. The publisher may want to rename the "stop cigarettes" trigger to reduce command ambiguity, but the inspected artifact is coherent and low risk.

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
93% confidence
Finding
The trigger phrase 'stop cigarettes' begins with the generic command word 'stop', which can collide with built-in assistant or runtime interruption commands. In practice, a user trying to halt the agent or cancel an action could accidentally invoke this skill instead, creating command ambiguity and reducing the reliability of safety-critical stop behavior.

Static analysis

No suspicious patterns detected.