Back to skill

Security audit

Ozon-店铺商品列表 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is narrowly aimed at querying Ozon shop product data, but it also tells the agent to install or upgrade Node.js and a CLI on the host without clear user approval.

Install only if you are comfortable letting the agent set up or upgrade Node.js and the qhkit CLI on your machine. Prefer a preinstalled, reviewed qhkit version and approve paid Qinghu API calls only after checking the estimated credits and requested shop parameters.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description says user requests of a broad class 'must trigger' the skill, but the activation criteria are underspecified. Over-broad mandatory triggering can cause the agent to invoke external tooling and paid operations in contexts where the user did not clearly request this specific capability, increasing the chance of unnecessary external calls and data exposure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation examples are short and vague, so they do not reliably distinguish this skill from other product-research or competitor-analysis workflows. In an agent system, such ambiguity can cause over-invocation of this skill, including paid API calls, when a broader or different workflow would be more appropriate.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This shop-query skill contains extensive instructions to install Node.js, globally install or upgrade a CLI, and modify the host environment if prerequisites are missing. That exceeds the minimum capability needed for answering a shop-products query and can lead an agent to perform unnecessary system changes, expanding attack surface and creating an avenue for unintended code execution from external package sources.

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 a specific version, which makes execution depend on whatever package version is current at runtime. That creates a supply-chain and reproducibility risk: a future compromised or breaking release could be fetched and executed during skill use.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
91% confidence
Finding

The duplicated finding reflects the same persistent-install behavior: creating directories under the home folder, extracting a runtime there, and exporting a modified PATH. Even if intended as convenience, this establishes lasting host-state changes inconsistent with a narrowly scoped query skill and can outlive the current task.

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
91% confidence
Finding

The duplicated finding reflects the same persistent-install behavior: creating directories under the home folder, extracting a runtime there, and exporting a modified PATH. Even if intended as convenience, this establishes lasting host-state changes inconsistent with a narrowly scoped query skill and can outlive the current task.

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.