Back to skill

Security audit

Ozon-二级类目查询 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is for Ozon category lookup, but it deserves review because it tells the agent to install or upgrade local tooling and configure a service token if dependencies are missing.

Install only if you are comfortable letting the agent set up qhkit/Node tooling and use a Qinghu API token. Prefer reviewing or approving any npm install, npx run, Node download, PATH change, qhkit upgrade, and token configuration before execution; also confirm paid qhkit calls and expected credit use before allowing lookups.

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
92% confidence
Finding

The trigger description includes broad language like '同类需求时必须触发', which can cause the skill to activate for loosely related requests. Over-broad invocation increases the chance that an agent executes the skill in unintended contexts, including contexts where installation, credential handling, or paid external calls are inappropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The listed trigger phrase '查二级类目 ID' is generic and does not uniquely bind to Ozon or this specific tool. In a multi-skill environment, that ambiguity can lead to accidental invocation of this skill for unrelated category-ID requests.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This skill's stated purpose is a simple category lookup, but it contains extensive environment bootstrap and software installation instructions, including installing Node, npm packages, and configuring credentials. That materially expands its authority and attack surface, enabling the skill to modify the host environment and persist tooling beyond what is necessary for a narrow data-query task.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The skill instructs the agent to execute npx @iqinghu/qhkit without pinning an exact package version, which can fetch whatever version is current at execution time. That creates a supply-chain and reproducibility risk: behavior can change unexpectedly, and a compromised or malicious package release could be executed in the user's environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
90% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking Node into the user's home directory and exporting a modified PATH. In the context of a category-query skill, persistent environment modification is unnecessary and increases long-term risk if the installed runtime or subsequent packages are abused.

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
90% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking Node into the user's home directory and exporting a modified PATH. In the context of a category-query skill, persistent environment modification is unnecessary and increases long-term risk if the installed runtime or subsequent packages are abused.

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

Static analysis

No suspicious patterns detected.