Back to skill

Security audit

Shopee-品牌类目分布 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Shopee analytics integration that installs and configures its required qhkit CLI, but users should review the setup steps before allowing persistent local changes.

Install only if you are comfortable allowing the agent to install qhkit or Node, make network calls to Qinghu and package registries, and store a qhkit API token locally. Confirm the Qinghu site/account region before changing configuration, and approve paid qhkit calls only after reviewing the estimated credit cost.

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)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

This analytics skill contains extensive host bootstrap instructions, including installing Node.js, globally installing packages, and modifying PATH, which exceeds the minimum privileges needed for a brand-category lookup. Such instructions normalize broad system changes and increase the chance an agent will perform unnecessary code execution and persistence on the host.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The phrase requiring the skill to trigger for 'similar needs' is overly broad and can cause the agent to invoke this skill outside its narrow intended scope. In context, over-triggering is more dangerous because the skill can initiate package installation, configuration changes, and paid external calls.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill recommends invoking an unpinned package via npx @iqinghu/qhkit, which allows execution of whatever version is current at runtime. That creates a supply-chain risk: a compromised latest release or dependency could execute arbitrary code in the host environment during a seemingly routine analytics task.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
90% confidence
Finding

This is a duplicate report of the same persistence behavior: installing Node into a user directory and altering PATH for subsequent command execution. Even with checksum verification, persisting new executables for a narrow business query is an unnecessary expansion of host capabilities.

Content

Scanner excerpt · SKILL.md (reported line 96)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
90% confidence
Finding

This is a duplicate report of the same persistence behavior: installing Node into a user directory and altering PATH for subsequent command execution. Even with checksum verification, persisting new executables for a narrow business query is an unnecessary expansion of host capabilities.

Content

Scanner excerpt · SKILL.md (reported line 96)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

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to set API tokens in local config and environment variables, and to guide users through credential acquisition and environment switching. Handling secrets and persistent auth state is broader than the business purpose and can lead to credential exposure, accidental overwrite of existing configuration, or misuse of higher-privileged accounts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

该说明明确要求本技能对接国内版 iqinghu.com,且当检测到 intl 配置时,默认要求用户改回 cn 并覆盖现有设置。虽然文档提到“只有用户明确说自己用的是国际版账号时才保留 intl”,但默认行为仍是强制单一区域配置,而非先提供区域选择或确认。

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

该部分给出“这个品牌主要做哪些品类”“品牌产品线分布”两个说法,但没有说明是否需要限定 Shopee 场景、品牌维度、类目分布意图等条件。缺少约束和反例会让相近但不适用的普通分析请求误触发该技能。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.