ClawHub
Back to skill

Security audit

Procrastination Buster

Security checks for vulnerabilities and agentic risk

Overview

This is a simple procrastination-help skill with disclosed local tracking and no code, network access, or hidden execution behavior.

Installers should be comfortable with the skill helping record commitments, blockers, and progress locally. Consider narrowing the trigger phrases if accidental activation would be distracting.

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 (2)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
93% confidence
Finding
The trigger "stop procrastinating" begins with the reserved/built-in command word "stop," creating a shadow-command conflict. In systems that prioritize or ambiguously parse built-in commands, this can interfere with expected stop/cancel behavior or cause the skill to activate when the user is trying to terminate another action, which is especially risky from a safety and control perspective.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrase set includes very common, everyday language such as "just start" and "procrastination help," which can cause the skill to activate unintentionally during normal conversation. This creates a control/UX security issue by increasing the chance of unexpected invocation, possibly hijacking unrelated user interactions or exposing task/accountability features in contexts where the user did not explicitly request them.

Static analysis

No suspicious patterns detected.