Back to skill

Security audit

Shopee-热搜词趋势 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate Shopee keyword-trend purpose, but it also tells the agent to install and upgrade host tooling and configure tokens automatically.

Install only if you are comfortable letting the skill use Qinghu qhkit, make paid Qinghu API calls after approval, and potentially install or upgrade Node/qhkit and store a qhkit token locally. Prefer using a preinstalled, reviewed qhkit version and avoid automatic @latest upgrades or profile/PATH changes unless you explicitly approve them.

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 trigger language says the skill 'must' activate for similar requests and lists broad keyword cues, making invocation boundaries fuzzy. Overbroad triggering can cause the agent to invoke this skill in contexts where it is unnecessary, leading to unintended external calls, billing, or host-side setup flows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation examples are short and generic, so they do not reliably distinguish this specialized skill from broader market-analysis requests. In practice this raises the chance of accidental invocation and unnecessary external tool usage, particularly because the skill also includes paid-call and environment setup instructions.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill’s stated purpose is a narrow keyword-trend lookup, but the document instructs broad host-level actions: installing Node, installing global packages, configuring tokens, changing PATH, and troubleshooting the local environment. This greatly expands the blast radius from a data query into arbitrary system modification and credential handling, which is risky in an agent-executed context.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific package version, which makes execution dependent on whatever version is current at runtime. That creates supply-chain risk and unpredictability, especially because the same document also directs installation and execution on the host environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
96% confidence
Finding

This duplicate finding points to the same environment-persistence behavior: installing software into the user home directory and modifying PATH for subsequent use. Even with checksum verification, the risk remains that a narrow analytics skill is expanding into host reconfiguration, increasing persistence and attack surface.

Content

Scanner excerpt · SKILL.md (reported line 94)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
96% confidence
Finding

This duplicate finding points to the same environment-persistence behavior: installing software into the user home directory and modifying PATH for subsequent use. Even with checksum verification, the risk remains that a narrow analytics skill is expanding into host reconfiguration, increasing persistence and attack surface.

Content

Scanner excerpt · SKILL.md (reported line 94)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

Static analysis

No suspicious patterns detected.