ClawHub
Back to skill

Security audit

淘宝官方导航

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Taobao-related link directory and does not request code execution, credentials, persistence, or local data access.

Before installing, users should treat it as a convenience directory for Taobao-related sites and verify important login or payment destinations in their browser, especially because the skill does not document explicit trigger conditions.

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
94% confidence
Finding

The skill has no defined activation criteria, so it may be invoked in contexts unrelated to Taobao navigation. Ambiguous triggering can cause unintended link output, user confusion, and over-broad execution of a skill that directs users to external websites.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

Natural-language policy review applies to all file types. Presenting the skill description and instructions exclusively in a single language can violate language-choice expectations when no opt-in, fallback, or justification is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.