ClawHub
Back to skill

Security audit

Shopping Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language shopping guidance skill with no executable code or hidden system access, though users should still handle purchases and shipping details carefully.

Install only if you want Chinese-language overseas-shopping guidance. Before acting on its recommendations, explicitly confirm any purchase, forwarding route, payment step, address disclosure, customs/tax obligation, return condition, and seller trust assessment yourself.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill describes proxy ordering and forwarding-route configuration but does not warn users about the financial, privacy, customs, and shipping risks inherent in those activities. In this context, omission of warnings is more dangerous because the skill domain directly touches payments, recipient information, package routing, and cross-border compliance, increasing the chance of user harm or misuse.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The invocation examples are overly broad and resemble natural conversation, which can cause the skill to trigger in situations beyond the user's clear intent. In a shopping/proxy-purchase context, unexpected activation is risky because it may lead the agent to engage in purchase guidance or logistics decisions involving money, shipping, or personal data without sufficiently explicit user confirmation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The description and user-facing instructions are entirely in Chinese, with no indication that the user can choose another language or that the skill is region-specific. This can violate a language/locale policy if the organization expects user choice rather than a forced language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.