ClawHub
Back to skill

Security audit

home-insurance-advisor

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language home insurance advice skill that asks for relevant household details and produces guidance, with no code execution or hidden data handling found.

Install this if you want Chinese-language home insurance guidance. Be aware it may ask about your home, assets, budget, and risk concerns; only provide details you are comfortable sharing, and treat its recommendations as general guidance rather than a substitute for formal policy terms or licensed advice.

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)

Vague Triggers

High
Confidence
96% confidence
Finding
The activation scope is overly broad and explicitly includes vague everyday phrases about protecting a home or valuables, which can cause the skill to trigger when the user did not actually request insurance advice. In an agent system, this creates unwanted context switching, unnecessary collection of personal housing/asset details, and increases the chance of steering unrelated conversations into a regulated financial domain.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The skill content is written as Chinese-only and does not provide a language fallback or user-choice mechanism, which can cause the agent to respond in a language the user did not request or understand. This is primarily a safety/UX control issue rather than a direct exploit, but it can still lead to user confusion, misunderstanding of insurance guidance, and accidental disclosure of sensitive information under false assumptions.

Static analysis

No suspicious patterns detected.