Back to skill

Security audit

Shopee-品牌店铺列表 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Shopee brand-shop lookup that uses the qhkit CLI and paid Qinghu data APIs, with setup steps that users should review before allowing installation or token configuration.

Before installing, confirm you trust the qhkit npm package and Qinghu account workflow. Expect the skill to install or use qhkit, ask for a Qinghu token if not configured, estimate paid credit use before calls, and potentially write tool/runtime files under the user environment if dependencies are missing.

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 (12)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger language includes vague phrases like 'or similar needs,' which can cause the skill to activate for loosely related requests. Overbroad activation is risky here because the skill can lead to package installation, credential setup, and external tool invocation, not just passive formatting or lookup.

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 13)May include surrounding context.

md
按品牌名查询售卖该品牌的热销店铺列表。

数据来自**青虎数据工具** `queryshopeebrandshoplist`(查品牌店铺列表,平台:Shopee),通过 `qhkit mcp` 调用——**不需要、也不要去宿主环境里找或配置 MCP server**。

## 何时触发

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 23)May include surrounding context.

md
按品牌名查询售卖该品牌的热销店铺列表。

数据来自**青虎数据工具** `queryshopeebrandshoplist`(查品牌店铺列表,平台:Shopee),通过 `qhkit mcp` 调用——**不需要、也不要去宿主环境里找或配置 MCP server**。

## 何时触发

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 24)May include surrounding context.

md
按品牌名查询售卖该品牌的热销店铺列表。

数据来自**青虎数据工具** `queryshopeebrandshoplist`(查品牌店铺列表,平台:Shopee),通过 `qhkit mcp` 调用——**不需要、也不要去宿主环境里找或配置 MCP server**。

## 何时触发

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 25)May include surrounding context.

md
按品牌名查询售卖该品牌的热销店铺列表。

数据来自**青虎数据工具** `queryshopeebrandshoplist`(查品牌店铺列表,平台:Shopee),通过 `qhkit mcp` 调用——**不需要、也不要去宿主环境里找或配置 MCP server**。

## 何时触发

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 73)May include surrounding context.

md
按品牌名查询售卖该品牌的热销店铺列表。

数据来自**青虎数据工具** `queryshopeebrandshoplist`(查品牌店铺列表,平台:Shopee),通过 `qhkit mcp` 调用——**不需要、也不要去宿主环境里找或配置 MCP server**。

## 何时触发

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is nominally a brand-shop query skill, but it contains extensive instructions to install software, configure tokens, and modify the host environment. That broadens the operational scope from data retrieval to host bootstrapping, increasing the chance an agent performs unnecessary privileged or security-sensitive actions on the user's machine.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a version, which makes execution depend on whatever package version is current at runtime. That creates supply-chain and reproducibility risk: a later compromised or breaking release could be fetched and executed on the host unexpectedly.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
94% confidence
Finding

This duplicate finding correctly identifies persistent host modification guidance: unpacking software under $HOME/.local/lib and exporting PATH changes runtime state and may lead to longer-lived setup when users follow nearby advice. Embedding such steps in a data-query skill unnecessarily expands the skill's authority and operational footprint.

Content

Scanner excerpt · SKILL.md (reported line 96)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
94% confidence
Finding

This duplicate finding correctly identifies persistent host modification guidance: unpacking software under $HOME/.local/lib and exporting PATH changes runtime state and may lead to longer-lived setup when users follow nearby advice. Embedding such steps in a data-query skill unnecessarily expands the skill's authority and operational footprint.

Content

Scanner excerpt · SKILL.md (reported line 96)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

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill hardcodes Chinese user-facing text to send to users, including credential guidance and follow-up instructions, without indicating that the language should match the user's preference. This creates a locale policy issue because it forces a specific language absent user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The documentation recommends persisting environment changes such as appending to ~/.bashrc, which is unrelated to the core query task and can affect future shell sessions. Persistent shell modifications increase blast radius by changing host behavior beyond the current invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.