Back to skill

Security audit

Shopee-子类目数据 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a real Shopee/Qinghu data-query helper, but it gives the agent broad setup authority to install runtime tools and configure credentials on the host.

Review this before installing if you do not want an agent to install or upgrade Node/qhkit, change PATH-related setup, or configure a Qinghu API token on your machine. Prefer a preinstalled, pinned qhkit version and provide explicit approval before any package installation, token configuration, or paid API call.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill 'must trigger' when the user uses two example phrases 'or makes similar requests', but it does not define what counts as similar. That ambiguity can cause unintended invocation for broadly related shopping or category-analysis requests.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill goes far beyond its stated purpose of querying Shopee subcategory data by directing installation of Node, global packages, token configuration, and environment repair steps. This expands the attack surface substantially: a simple data-query skill should not be modifying the host environment, installing software, or steering credential setup flows.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which can fetch and execute whatever package version is current at runtime. In a skill that already performs environment bootstrapping and installs tooling, this increases supply-chain risk and makes behavior non-reproducible.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
93% confidence
Finding

This duplicate finding flags the same persistent environment modification: unpacking Node into $HOME/.local/lib and exporting a modified PATH. In the context of an agent skill, instructions that alter the host runtime exceed least privilege and make the skill materially more dangerous than a simple API-query helper.

Content

Scanner excerpt · SKILL.md (reported line 95)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
93% confidence
Finding

This duplicate finding flags the same persistent environment modification: unpacking Node into $HOME/.local/lib and exporting a modified PATH. In the context of an agent skill, instructions that alter the host runtime exceed least privilege and make the skill materially more dangerous than a simple API-query helper.

Content

Scanner excerpt · SKILL.md (reported line 95)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
86% confidence
Finding

The text instructs the agent to require site be cn, direct users to Chinese domestic login/API-key URLs, and avoid international configuration unless the user explicitly says they use AutoAGC. This imposes a specific locale/account environment by default rather than offering a user choice or clearly framing it as an opt-in regional variant.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.