Back to skill

Security audit

电商详情页复刻 | 详情页模仿 | 高转化设计 | 竞品详情 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed e-commerce image-generation helper with normal tool-install, API-token, image-upload, and imitation-style risks users should understand.

Install only if you are comfortable using the qhkit npm package, providing a qhkit token, and uploading product/reference images to the service. Use it for inspired layout and style adaptation, not copying another seller's logos, branding, protected artwork, or distinctive trade dress.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is explicitly designed around '复刻/模仿/对标竞品' behavior with broad trigger language and weak boundaries. In context, this increases the chance the agent will help users imitate competitor creative works too closely, creating IP/compliance risk and enabling misuse of the tool for deceptive cloning rather than original design assistance.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs the agent to execute npx @iqinghu/qhkit without pinning an exact package version. That creates a supply-chain risk because every invocation may fetch whatever package version is current at execution time, allowing unexpected behavior changes or compromise if the package or dependency chain is tampered with.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

This duplicated finding points to the same persistence behavior: unpacking Node into a user directory and exporting a modified PATH. While the skill includes checksum verification, the behavior still establishes reusable local tooling beyond the task scope, which is risky in an agent setting because it normalizes self-bootstrapping and persistent environment alteration.

Content

Scanner excerpt · SKILL.md (reported line 49)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
88% confidence
Finding

This duplicated finding points to the same persistence behavior: unpacking Node into a user directory and exporting a modified PATH. While the skill includes checksum verification, the behavior still establishes reusable local tooling beyond the task scope, which is risky in an agent setting because it normalizes self-bootstrapping and persistent environment alteration.

Content

Scanner excerpt · SKILL.md (reported line 49)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
95% confidence
Finding

The instruction says to relay CLI error messages to users because they are already user-facing Chinese, implying a fixed Chinese-language response behavior. There is no indication that users can choose another language or that the language restriction is optional.

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 gives only two positive examples and no negative examples or non-trigger cases. This makes it unclear how the skill distinguishes between exact page-cloning requests and broader, non-cloning design assistance.

Content

No source excerpt is available for this finding.