Back to skill

Security audit

Shopee-商品榜单 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is for Shopee ranking queries, but it also tells the agent to install software, change the local environment, and handle an API token, so it should be reviewed before use.

Install only if you are comfortable with the agent installing Node/qhkit, modifying the user environment, and configuring a qhkit API token for a paid external service. Prefer a disposable environment or preinstalled, pinned qhkit version, and require explicit approval before any install, token setup, upgrade, or paid 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 trigger definition is broad and says the skill 'must' activate for similar requests, making accidental invocation more likely. In combination with the skill's install/configure behavior and paid external calls, overly broad triggering can cause unnecessary tool use, host changes, or credential prompts from ordinary conversation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The sample trigger phrases are generic enough that normal discussion of Shopee trends or hot products could invoke the skill. Because the skill can lead to paid API usage and environment setup steps, low-specificity triggers increase the chance of unsafe or unauthorized actions.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill goes well beyond querying product rankings and instructs the agent to install Node, install global packages, configure API tokens, and modify the host environment. That materially expands the attack surface from data retrieval to host-level software installation and credential handling, which is dangerous if the skill is triggered in an untrusted or sensitive environment.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows execution of whatever package version is current at runtime. In a skill context, this creates a supply-chain risk because behavior can change unexpectedly or a compromised upstream release could execute arbitrary code on the host.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This repeated finding describes persistent installation into a user directory and shell path modification, which survives beyond the immediate task. Such persistence is especially risky here because it is bundled into routine skill guidance, normalizing host alteration for a simple data-query workflow.

Content

Scanner excerpt · SKILL.md (reported line 102)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 repeated finding describes persistent installation into a user directory and shell path modification, which survives beyond the immediate task. Such persistence is especially risky here because it is bundled into routine skill guidance, normalizing host alteration for a simple data-query workflow.

Content

Scanner excerpt · SKILL.md (reported line 102)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.