Back to skill

Security audit

Shopee-店铺长期趋势 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Shopee shop-trend lookup tool, but it also directs automatic installation, upgrades, PATH changes, and credential setup that should be reviewed before use.

Install only if you are comfortable letting this skill set up qhkit/Node and store a Qinghu API token. Prefer preinstalling and reviewing qhkit yourself, avoid unpinned npx or @latest upgrades where possible, and approve paid API calls only after the agent states the tools and expected Qinghu credit use.

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 (8)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says similar requests 'must trigger' the skill using broad language, which can cause the agent to invoke this paid, tool-using workflow for loosely related user queries. Overbroad activation increases the chance of unnecessary external calls, data handling, and billing without clear user intent.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
## 工具说明(线上原文整理)

通过店铺ID查询热销店铺的历史趋势数据。入参 shopId 由 `queryshopeeshopdata`、`queryshopeeshopranking`、`queryshopeebrandshoplist` 等接口返回。支持按月(granularity=month)、季度(granularity=quarter)、年(granularity=year)颗粒度统计。支持按类目筛选(categoryId+level)、产品类型筛选(productType)、商品所在地筛选(borderType)。最长可支持查看过去720天。相比 `queryshopeeshoptrend`(按天返回),该接口支持聚合颗粒度,更适合长期趋势分析。可选站点:tw(台湾)、my(马来西亚)、id(印度尼西亚)、th(泰国)、ph(菲律宾)、sg(新加坡)、vn(越南)、br(巴西)。

## 上下游

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
## 工具说明(线上原文整理)

通过店铺ID查询热销店铺的历史趋势数据。入参 shopId 由 `queryshopeeshopdata`、`queryshopeeshopranking`、`queryshopeebrandshoplist` 等接口返回。支持按月(granularity=month)、季度(granularity=quarter)、年(granularity=year)颗粒度统计。支持按类目筛选(categoryId+level)、产品类型筛选(productType)、商品所在地筛选(borderType)。最长可支持查看过去720天。相比 `queryshopeeshoptrend`(按天返回),该接口支持聚合颗粒度,更适合长期趋势分析。可选站点:tw(台湾)、my(马来西亚)、id(印度尼西亚)、th(泰国)、ph(菲律宾)、sg(新加坡)、vn(越南)、br(巴西)。

## 上下游

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill goes beyond querying shop trends and instructs installation of Node/qhkit, configuration changes, token setup, PATH modification, and package upgrades. This expands the agent's authority from data retrieval into environment bootstrap and persistent system modification, increasing risk of unintended changes and supply-chain exposure.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The skill instructs the agent to execute npx @iqinghu/qhkit without pinning an exact package version. That allows behavior to change over time and exposes execution to supply-chain risk if a newer package version is compromised or unexpectedly introduces unsafe functionality.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This is a duplicate of the persistence issue at line 98: installing binaries under the user's home directory and exporting a modified PATH extends the skill's effects beyond the session. In context, that is disproportionate to the stated business purpose and increases the chance of unauthorized or hard-to-audit system changes.

Content

Scanner excerpt · SKILL.md (reported line 98)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 is a duplicate of the persistence issue at line 98: installing binaries under the user's home directory and exporting a modified PATH extends the skill's effects beyond the session. In context, that is disproportionate to the stated business purpose and increases the chance of unauthorized or hard-to-audit system changes.

Content

Scanner excerpt · SKILL.md (reported line 98)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 '何时触发' section provides two examples, but does not define when the skill should not activate or how narrowly '店铺长期趋势' requests are interpreted. Without explicit exclusions or constraints, invocation criteria remain ambiguous.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.