Back to skill

Security audit

Shopee-热搜词库筛选 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill does the Shopee keyword lookup it claims, but it also tells the agent to make persistent local tool, Node, PATH, and credential/configuration changes that users should review first.

Review this before installing if you do not want an agent to install Node/qhkit, change PATH, or alter qhkit token/environment configuration on your machine. Prefer using a preinstalled, pinned qhkit version in an isolated environment and provide credentials only through a trusted secret flow. The reviewed artifact does not show deception, exfiltration, destructive behavior, or hidden code execution, but its local setup authority is broader than a simple keyword-query skill.

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
94% confidence
Finding

The manifest says the skill 'must trigger' when the user says the listed phrases 'or提出同类需求', which leaves the activation boundary undefined. This can overlap with many ordinary Shopee-related requests and may cause unintended invocation because there are no exclusion conditions or negative examples.

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 well beyond querying Shopee keyword data and directs broad environment bootstrapping: installing Node, installing global packages, modifying PATH, and changing local CLI state. For a filtering-only skill, these host-modifying actions are over-scoped and dangerous because they increase the attack surface and can persistently alter the user's machine for a task that should be limited to a narrowly scoped tool call.

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 a specific version, which permits whatever package version is current at execution time to run. That creates supply-chain and reproducibility risk: a compromised or breaking upstream release could execute unexpected code in the user's environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
93% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking software into the user's home directory and exporting a modified PATH. Such host-state changes are not justified by the skill's declared purpose and increase risk by establishing durable execution capability beyond the current session.

Content

Scanner excerpt · SKILL.md (reported line 106)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 points to the same persistence behavior: unpacking software into the user's home directory and exporting a modified PATH. Such host-state changes are not justified by the skill's declared purpose and increase risk by establishing durable execution capability beyond the current session.

Content

Scanner excerpt · SKILL.md (reported line 106)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
97% confidence
Finding

The skill instructs the agent to set API tokens and manipulate environment-based configuration (qhkit config set --token, QHKIT_TOKEN, QHKIT_ENV). This is security-sensitive credential handling unrelated to the stated keyword-filtering purpose and could lead to credential exposure, overwriting existing configuration, or steering requests to unintended environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.