ClawHub
Back to skill

Security audit

Quit Overspending

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local overspending-support skill with no executable code, network behavior, or hidden authority.

Install only if you are comfortable having the assistant track spending urges, savings goals, and related habit notes locally. Be aware that the 'stop overspending' trigger could be confused with a cancellation-style command in some environments, but this is a usability concern rather than evidence of malicious behavior.

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
91% confidence
Finding

The trigger phrase 'stop overspending' begins with the generic command word 'stop', which can collide with built-in stop/cancel handling in assistant frameworks. This can cause the skill to intercept or confuse a user's intent to cancel an action, creating reliability and safety issues through command shadowing even though the skill itself is otherwise low-risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.