ClawHub
Back to skill

Security audit

Shopee-品牌站点分布 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Shopee analytics integration, but it asks agents to install unpinned tools, modify the user environment, and configure API credentials for a narrow lookup task.

Review this before installing if you are comfortable with a third-party qhkit CLI, npm/global or npx execution, persistent local tool setup, and qhkit API token configuration. Prefer a preinstalled, pinned qhkit version and use a scoped token; confirm charges before any paid calls.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description includes broad trigger language such as similar requests and multiple keywords, which can cause the skill to activate in contexts not clearly requesting this specific capability. Over-broad invocation is risky here because the skill contains installation, configuration, and paid external-call instructions, so unintended triggering can lead to unnecessary tool use or environment changes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger phrase '品牌站点布局' is vague and could match many unrelated analytical or marketing requests. In this skill, vague triggering is more concerning because activation can cascade into external CLI usage, pricing/authorization flows, and setup guidance not warranted by an ambiguous request.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This skill goes beyond a read-only analytics task and directs the agent to install Node.js and globally install a CLI in the host environment. Host modification expands the attack surface, introduces persistence, and allows unreviewed third-party code execution for a task that should be satisfied through constrained tool use rather than environment bootstrapping.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
84% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific package version, so execution may pull whatever version is current at runtime. That creates supply-chain and reproducibility risk, especially because the package is then used to access external services and potentially handle credentials.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicated finding still reflects persistent environment modification through installation into $HOME/.local/lib and PATH changes. The context makes it a real issue because the skill is for data lookup, yet it encourages durable host customization that can outlive the session and affect future commands.

Content

Scanner excerpt · SKILL.md (reported line 92)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
92% confidence
Finding

This duplicated finding still reflects persistent environment modification through installation into $HOME/.local/lib and PATH changes. The context makes it a real issue because the skill is for data lookup, yet it encourages durable host customization that can outlive the session and affect future commands.

Content

Scanner excerpt · SKILL.md (reported line 92)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
95% confidence
Finding

The skill instructs the agent to set API tokens via CLI or environment variables, which grants credential-handling capability not necessary for a narrow brand-distribution query. This can expose secrets to logs, shell history, environment inheritance, or accidental reuse by other processes and materially increases the blast radius if the skill or dependency is compromised.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.