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 is a disclosed Amazon product analysis skill that uses a Qinghu API token and asks for user approval before paid data calls.

Install only if you intend to use Qinghu for Amazon product research. Review the first authorization prompt carefully because it approves the listed tools for the current session, and understand that your ASIN/link data and Qinghu API token are used with the Qinghu service and that large results may be exported to local files.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger section includes broad conversational phrases like “这个链接怎么样” and “帮我分析下这个竞品”, which are generic enough to match many ordinary shopping or discussion requests. Because this skill is user-invocable and can lead to external API usage and potential paid calls, over-broad triggering increases the risk of accidental invocation, unnecessary data access, and unwanted cost-incurring actions.

Content

No source excerpt is available for this finding.