ClawHub
Back to skill

Security audit

亚马逊-关键词选品专家 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Amazon keyword research skill that uses the Qinghu API with user approval before external tool calls; no hidden code, persistence, or destructive behavior was found.

Install only if you intend to use Qinghu for Amazon keyword research. Expect to provide or expose a Qinghu API token, approve tool usage before calls, and potentially spend Qinghu credits; review the requested marketplace, tools, and estimated cost before confirming.

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
91% confidence
Finding

The trigger examples are broad, natural-language phrases like '帮我挖点关键词' and '这个词值得做吗', which can overlap with ordinary shopping, SEO, or research requests and cause the skill to activate when the user did not specifically intend to use this integration. In this skill, unintended invocation is more concerning because activation can lead to requests for API credentials and potentially paid external tool usage, increasing the risk of unnecessary data access or charges.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions say to translate user-provided category terms into the target marketplace language before proceeding, and elsewhere state '先翻成站点语言再挖'. This imposes a language/locale choice by default rather than offering the user a choice or documenting an explicit justified locale constraint.

Content

No source excerpt is available for this finding.