ClawHub
Back to skill

Security audit

Refrigerator Buying Consultant

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only refrigerator buying advisor with disclosed, purpose-aligned questions and no executable or persistent behavior.

Before installing, understand that the skill will ask practical buying questions such as household size, kitchen measurements, country/city, and power stability. Treat product models and energy-label references as starting points and verify local availability, exact specifications, pricing, and the applicable local energy-rating standard before purchasing.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The instruction hard-codes regional rating schemes as '3-star BEE or higher (South Asia) / A+ or higher (EU/UK)' as the expected output format. This can impose a specific locale/standards framing on users without checking their country-specific labeling system or offering alternatives, which is a natural-language locale policy concern.

Static analysis

No suspicious patterns detected.