ClawHub
Back to skill

Security audit

亚马逊-爆款趋势挖掘师 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Amazon product-research helper that uses Qinghu data APIs with user confirmation and does not include hidden execution or persistence.

Before installing, expect this skill to ask for or use a Qinghu API token and to call Qinghu's external data endpoint, which may consume Qinghu credits after you approve the planned tools. Review the planned calls and marketplace/category scope before authorizing, especially if your request could fit another Amazon-focused skill.

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 skill description says certain common Amazon product-research requests 'must trigger,' which creates an overly broad activation scope. In a multi-skill environment, this can cause the skill to intercept requests beyond its proper boundary, leading to unintended tool use, unnecessary credential prompts, or paid API calls without the most appropriate skill being selected.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger examples are broad and provide only positive activation cues, without negative examples or exclusion rules. This ambiguity increases the chance of accidental invocation for generic shopping, market research, or adjacent Amazon-analysis requests, which is more concerning here because the skill is designed to request tokens and invoke external data tools that may incur cost.

Static analysis

No suspicious patterns detected.