Back to skill

Security audit

Shopee-三级类目查询 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill performs the Shopee category lookup it claims to, but it also tells the agent to install or upgrade local command-line tooling and configure an API token.

Install only if you are comfortable with qhkit, Node/npm setup, persistent local configuration, and paid API calls. Prefer approving any install or upgrade step explicitly, using a contained environment, and pinning trusted package versions where possible.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition includes a broad catch-all phrase equivalent to 'or similar requests must trigger', which creates ambiguous invocation boundaries. In practice, this can cause the skill to activate for loosely related requests and lead to unnecessary external calls, cost-incurring actions, or execution of the skill's bootstrapping/install behavior when the user did not clearly request it.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This skill is nominally a category-query skill, but it contains extensive environment bootstrapping logic: installing Node, installing npm packages globally, configuring credentials, upgrading tooling, and altering runtime behavior. That broadens the skill from data retrieval into system modification and remote package execution, increasing attack surface and making unintended host changes much more likely.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs the agent to execute npx @iqinghu/qhkit without pinning an exact package version, which allows whatever version is current at execution time to be fetched and run. In an agent context, this materially expands supply-chain risk because remote code is being installed and executed on demand, and the skill also frames this as an acceptable fallback during task execution.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This duplicate finding points to the same persistent-install behavior: extracting a runtime into a user-controlled directory and prepending it to PATH. In the context of an agent skill, persistence is especially risky because a one-time invocation can leave behind tooling that affects later commands and sessions, exceeding the expected scope of a read-only category lookup.

Content

Scanner excerpt · SKILL.md (reported line 91)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
95% confidence
Finding

This duplicate finding points to the same persistent-install behavior: extracting a runtime into a user-controlled directory and prepending it to PATH. In the context of an agent skill, persistence is especially risky because a one-time invocation can leave behind tooling that affects later commands and sessions, exceeding the expected scope of a read-only category lookup.

Content

Scanner excerpt · SKILL.md (reported line 91)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

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

示例调用直接固定 "language":"zh-CN",而文档虽列出多种可选语言,但没有明确要求按用户语言或地区偏好选择,容易让执行者默认始终使用中文。根据规则,未经用户选择即强制特定语言/locale 可能构成自然语言策略问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.