ClawHub
Back to skill

Security audit

Build Discipline

Security checks for vulnerabilities and agentic risk

Overview

This is a simple self-improvement skill with disclosed local habit tracking and no bundled code, network behavior, or hidden install mechanism.

Before installing, be aware that the skill may keep local notes about your habits, commitments, streaks, and check-ins. If accidental activation matters to you, consider narrowing the trigger phrases or using it only when you explicitly want discipline tracking.

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
97% confidence
Finding
The trigger 'build discipline' begins with the built-in command keyword 'build', creating a shadowing/confusion risk where the custom skill may intercept or be confused with built-in command execution. This can cause misrouting of user intent and unexpected skill activation, especially in systems where command resolution prioritizes prefix matches or ambiguous triggers.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger phrases are common self-improvement language and are broad enough to match ordinary conversation, which can cause the skill to activate unintentionally. Because the skill claims it can store commitments and reminders, accidental invocation may lead to unexpected data handling or interference with the user's intended command flow.

Static analysis

No suspicious patterns detected.