ClawHub
Back to skill

Security audit

亚马逊-ASIN解析专家 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Amazon product-analysis helper that uses the Qinghu API with user-provided credentials and requires user approval before paid calls.

Install only if you intend to use Qinghu's Amazon data service. Be prepared to provide a Qinghu API key or set QINGHU_TOKEN/QHKIT_TOKEN, and review the listed tools and estimated point costs before approving calls. For best results, invoke it with an Amazon ASIN or product URL to avoid accidental activation from generic competitor-analysis requests.

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
Confidence
93% confidence
Finding
The trigger examples include broad everyday phrases like '这个链接怎么样' and '帮我分析下这个竞品', which can match many unrelated conversations and cause the skill to activate unexpectedly. Because this skill is user-invocable and can lead to external API usage and paid tool calls, over-triggering increases the risk of unintended data access, confusing routing, and unnecessary cost.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The description says requests like competitor checkups 'must trigger' without defining boundaries or exclusions, creating an overly aggressive routing rule. In context, this is more dangerous because the skill instructs the agent to collect credentials, call third-party endpoints, and potentially incur charges, so a false activation has real operational and billing consequences.

Static analysis

No suspicious patterns detected.