ClawHub
Back to skill

Security audit

lingxiao-product-selection

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language cross-border e-commerce product-selection guide that connects to a named MCP service and does not include hidden code, persistence, or destructive behavior.

Install this only if you are comfortable adding the Lingxiao MCP endpoint and sharing product-selection inputs with that service. Use an API key only if you trust the provider account flow and need higher limits or paid data tools.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation text is broad enough to trigger on many generic product-selection or evaluation requests, which can cause the agent to invoke this skill outside a narrowly intended context. Over-broad routing is dangerous because it can override more appropriate skills or inject external-tool-driven workflows into unrelated conversations, increasing the chance of incorrect guidance or unnecessary data exposure to the linked MCP service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill content and user-facing description are written only in Chinese, with no indication that users may choose another language or that the skill is intended exclusively for Chinese-speaking users. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale limitation is explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.