ClawHub
Back to skill

Security audit

中国电商搜索

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed shopping-search helper for Chinese e-commerce platforms, with no code, persistence, credential handling, or hidden execution behavior.

Before installing, understand that this skill will guide an agent to open multiple Chinese shopping platforms and compare listings. Do not let an agent place orders, change account details, or use saved payment methods unless you give a separate explicit confirmation for that specific transaction.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly ends with a prompt to help place an order, which nudges the user toward a transactional action without a safety boundary, confirmation flow, or warning that purchasing may affect accounts, payment methods, or saved addresses. In a shopping skill, this increases the chance of unintended account-affecting actions, especially if the agent is later granted browser or commerce capabilities.

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
L203 states '支持中文交流', and the skill content is written to operate in Chinese without offering alternative language handling or an explicit user choice. Under the stated policy, forcing or assuming a specific language without opt-in can be a natural-language policy violation unless the locale restriction is clearly documented and justified.

Static analysis

No suspicious patterns detected.