ClawHub
Back to skill

Security audit

Xianyu Auto Seller

Security checks for vulnerabilities and agentic risk

Overview

This is a marketplace copywriting and workflow skill for Xianyu listings, with no executable code, persistence, credential access, or hidden automation.

Install this if you want help drafting Chinese Xianyu listings and shop replies for digital goods. Review generated listings for copyright, platform-rule, and consumer-protection compliance, especially around course resale, software, automated delivery, refund wording, and revenue claims.

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

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description states the skill is for optimizing listings on China's Xianyu marketplace, and the document consistently provides Chinese-language listing text and reply scripts as the default behavior. Because the skill does not offer a language or locale choice, it imposes a specific locale on generated content rather than making that constraint explicit as an opt-in or justified regional limitation in the instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.