Back to skill

Security audit

Shopee-品牌库筛选 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill does the promised Shopee brand lookup, but it also directs local tool installation, upgrades, PATH changes, and API-token configuration, so it needs user review before install.

Install only if you trust the Qinghu qhkit npm package and are comfortable with local npm/Node setup, paid API calls, and storing a qhkit token locally. Prefer a pre-provisioned or pinned qhkit version, approve any install or upgrade separately, and avoid pasting long-lived tokens into chat unless your platform handles secrets safely.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrase 'or similar requests must trigger' is overly broad and can cause the skill to activate for loosely related requests without clear user intent. In this skill, over-triggering is more dangerous because activation can lead to paid tool calls, dependency installation, and credential/configuration guidance.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
提供 Shopee 离线(T+1更新)库的品牌数据。支持按类目(categoryId+level)、品牌名称模糊搜索(brandName)筛选。支持按相关产品数(sortType=1)、近30天销量(sortType=2)、近30天销售额(sortType=3)、相关店铺数(sortType=4)排序。入参 categoryId 和 level 由类目查询接口返回。返回的品牌名称(brandName)可作为入参传递给:
- `queryshopeebrandtrend`:查看品牌历史趋势
- `queryshopeebranddetailbatch`:批量获取品牌详情
- `queryshopeebrandshoplist`:查看品牌下的店铺列表
- `queryshopeebrandpricedistribute`:查看品牌价格分布
- `queryshopeebrandsitedistribute`:查看品牌站点分布

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
提供 Shopee 离线(T+1更新)库的品牌数据。支持按类目(categoryId+level)、品牌名称模糊搜索(brandName)筛选。支持按相关产品数(sortType=1)、近30天销量(sortType=2)、近30天销售额(sortType=3)、相关店铺数(sortType=4)排序。入参 categoryId 和 level 由类目查询接口返回。返回的品牌名称(brandName)可作为入参传递给:
- `queryshopeebrandtrend`:查看品牌历史趋势
- `queryshopeebranddetailbatch`:批量获取品牌详情
- `queryshopeebrandshoplist`:查看品牌下的店铺列表
- `queryshopeebrandpricedistribute`:查看品牌价格分布
- `queryshopeebrandsitedistribute`:查看品牌站点分布

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill goes far beyond querying a brand list and instructs the agent to install Node, install packages globally, change PATH, and alter local runtime configuration. Those actions expand the attack surface substantially and can persist changes on the host, which is dangerous for a data-query skill that should be narrowly scoped.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows execution of whatever package version is current at invocation time. In a skill context that also directs installation and credential handling, this increases supply-chain risk because behavior can change or a compromised release could be fetched and run unexpectedly.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicate finding correctly identifies persistent local installation and PATH modification instructions. In context, the skill's environment self-bootstrapping makes the persistence more dangerous because it encourages host mutation as part of normal execution.

Content

Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicate finding correctly identifies persistent local installation and PATH modification instructions. In context, the skill's environment self-bootstrapping makes the persistence more dangerous because it encourages host mutation as part of normal execution.

Content

Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill directs the agent to obtain, set, and troubleshoot API tokens and environment variables, including telling the user where to retrieve credentials and how to inject them into the CLI environment. Having a user-facing skill handle secrets collection and local credential configuration is risky because it normalizes credential handling by the agent and can lead to secret exposure or misuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instructions direct the agent to use domestic Chinese login pages, Chinese key-retrieval guidance, and explicitly prefer the China-site configuration unless the user states otherwise. This imposes a locale-specific workflow by default rather than offering a language or region choice, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The “何时触发” section provides only positive examples and no negative examples or explicit limits on when the skill should not run. Without exclusions, a broad phrase like “类目品牌排行” may ambiguously match requests that need a different tool, broader analysis, or another platform.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.