ClawHub
Back to skill

Security audit

Ozon-类目市场销售数据 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for Ozon category sales queries, but it also instructs agents to install and update external tooling and configure a paid-service token on the host.

Review and approve setup steps before using this skill. It should only be allowed to install qhkit or Node, change PATH, or configure a qhkit token when you intentionally want this paid Qinghu/Ozon data integration on that machine.

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
  • 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 mandates activation for broad, loosely defined similar requests, which can cause over-invocation of a paid external tool and unnecessary data access. In this skill's context, broad triggering is especially risky because invocation may lead to software installation, credential setup, and billable remote calls, so an ambiguous request could cascade into actions the user did not clearly intend.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill goes far beyond its stated purpose of querying category sales data by directing installation of Node, global packages, token configuration, PATH changes, and environment modifications. This expands the attack surface substantially and can lead to unauthorized software installation, credential handling, and persistent host changes in environments where a simple data-query skill should not be performing system bootstrap.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, so execution may fetch whatever package version is current at runtime. That creates a supply-chain and reproducibility risk: a compromised or breaking upstream release could be executed in the user's environment with the skill implicitly authorizing it.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
94% confidence
Finding

This duplicated finding points to the same persistence behavior: unpacking software into a user-controlled directory and exporting a modified PATH. Such instructions normalize host modification and create a lasting foothold for externally fetched tooling, which is disproportionate to the skill's stated function.

Content

Scanner excerpt · SKILL.md (reported line 99)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
94% confidence
Finding

This duplicated finding points to the same persistence behavior: unpacking software into a user-controlled directory and exporting a modified PATH. Such instructions normalize host modification and create a lasting foothold for externally fetched tooling, which is disproportionate to the skill's stated function.

Content

Scanner excerpt · SKILL.md (reported line 99)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

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The '何时触发' section provides two sample utterances, one of which is common conversational phrasing in context ('这个细分类目卖了多少'), but it does not clarify when the skill should not activate. Without explicit exclusions or tighter scope language, agents may over-apply the skill to related but unsupported category-analysis requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.