Back to skill

Security audit

亚马逊-类目节点查询 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to perform the advertised Amazon category lookup, but it also tells agents to install or upgrade command-line software and Node in the user's environment automatically.

Review this carefully before installing. It is not showing evidence of theft or sabotage, but it may download and install Node/qhkit, alter PATH for the session or shell, upgrade packages, and store a qhkit token. Prefer a controlled environment with preinstalled, pinned qhkit and provide API credentials only when you understand the credit charges.

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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The instruction says to translate the keyword into the target site's or country's language before calling the tool. This imposes a language/locale transformation by default rather than offering the user a choice, which can conflict with language/locale policy expectations.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill is supposed to query Amazon category nodes, but it also instructs the agent to install Node, install packages globally, configure tokens, and modify the runtime environment. Expanding from data lookup into software installation materially enlarges the attack surface and could cause unreviewed code execution on the host.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill recommends running npx @iqinghu/qhkit without pinning an exact version. That causes execution of whatever package version is current at invocation time, increasing supply-chain risk and making behavior non-reproducible if a compromised or breaking release is published.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
86% confidence
Finding

The duplicated finding reflects the same persistence issue: the documented setup stores Node in the user's home directory and modifies execution paths as part of fulfilling a simple lookup skill. That is risky because a narrowly scoped skill should not normalize persistent host modification to satisfy routine requests.

Content

Scanner excerpt · SKILL.md (reported line 100)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
86% confidence
Finding

The duplicated finding reflects the same persistence issue: the documented setup stores Node in the user's home directory and modifies execution paths as part of fulfilling a simple lookup skill. That is risky because a narrowly scoped skill should not normalize persistent host modification to satisfy routine requests.

Content

Scanner excerpt · SKILL.md (reported line 100)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

Static analysis

No suspicious patterns detected.