Back to skill

Security audit

Shopee-站点类目数据 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed connector for paid Qinghu Shopee category data, with the main risks being setup of qhkit/Node, token configuration, and paid API calls.

Before installing, confirm you are comfortable installing qhkit/Node from the disclosed sources and providing a Qinghu API token. Approve paid qhkit calls only when the requested Shopee site, date, level, and estimated charge are clear; using a preinstalled or pinned qhkit version would reduce supply-chain uncertainty.

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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says similar requests 'must trigger' and includes broad keywords, making invocation boundaries loose. Over-broad activation can cause the agent to invoke this paid external tool in contexts where it is unnecessary, leading to unintended data disclosure, needless external calls, or unauthorized charges.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill exceeds its stated data-query purpose by directing installation of Node/qhkit, persistent PATH changes, and API token configuration on the host. This materially increases attack surface and can lead an agent to modify the environment, introduce new software, and handle secrets, all of which are risky in a skill that should be limited to querying category data.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows whatever version is current at execution time to be fetched and run. That creates supply-chain risk and undermines reproducibility, especially because the fetched package is then used to access external services and credentials.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicate finding identifies the same persistence behavior: unpacking Node into the user's home directory and exporting a new binary path. In the skill context, that is unnecessarily invasive and increases long-term trust in newly downloaded binaries, which is disproportionate to a simple data-retrieval function.

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
92% confidence
Finding

This duplicate finding identifies the same persistence behavior: unpacking Node into the user's home directory and exporting a new binary path. In the skill context, that is unnecessarily invasive and increases long-term trust in newly downloaded binaries, which is disproportionate to a simple data-retrieval function.

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

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The example trigger '各类目的销量对比' is generic and could refer to many contexts, sites, platforms, or datasets beyond this specific Shopee site-level category tool. Without requiring Shopee, site, level, or dataset context in the trigger guidance, it risks unintended activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.