ClawHub
Back to skill

Security audit

Car Rental

Security checks for vulnerabilities and agentic risk

Overview

This car-rental skill is a disclosed, purpose-aligned markdown guide that stores optional local preferences only with user permission.

Install only if you want an assistant to remember local car-rental preferences and searches. Review the proposed ~/car-rental/ memory files and only enable periodic alerts or broad travel-triggered help if that matches how you want the skill to behave.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Content
integration: pending

## Preferences
<!-- Add as you learn from conversations -->

### Vehicle
<!-- car class, transmission, fuel type, features -->
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill explicitly suggests activating whenever the user mentions 'car rentals or travel,' which is broader than the skill’s stated purpose and can cause the agent to engage on generic travel discussions without clear user intent. Over-broad activation increases the chance of unsolicited behavior, unnecessary data collection, and accidental persistence of user preferences in contexts the user did not mean to invoke this skill.

Static analysis

No suspicious patterns detected.