Back to skill

Security audit

Ozon-一级类目查询 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Ozon category lookup tool, but it asks the agent to install and configure host-level tooling with persistent credentials and unpinned runtime dependencies.

Review this skill before installing if you do not want an agent to install Node/npm packages, alter PATH or shell profile behavior, or store a qhkit token on your machine. If you use it, prefer a preinstalled, pinned qhkit version in an isolated environment and confirm any paid qhkit call before it runs.

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 manifest description says the skill 'must trigger' not only for two example phrases but also for '同类需求', which is ambiguous and expands activation beyond clearly defined requests. This can cause unintended invocation because it does not specify exclusion conditions or concrete limits for what counts as a similar request.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill goes far beyond querying category data by directing the agent to install Node.js, globally install a CLI, configure credentials, and modify the host environment. For a simple lookup skill, these instructions unnecessarily expand the trusted computing base and create opportunities for unauthorized software installation, persistence, credential handling, and supply-chain compromise.

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 makes execution depend on whatever package version is current at runtime. That creates a supply-chain and reproducibility risk: a future compromised or breaking release could be fetched and executed in the host environment during skill use.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
94% confidence
Finding

This duplicate finding points to the same persistence behavior: unpacking software into a user-controlled directory and altering PATH to make it executable in future shell contexts. In the context of a category-query skill, persisting tooling on the host is disproportionate and materially increases risk if the installed component or follow-on commands are compromised.

Content

Scanner excerpt · SKILL.md (reported line 90)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 duplicate finding points to the same persistence behavior: unpacking software into a user-controlled directory and altering PATH to make it executable in future shell contexts. In the context of a category-query skill, persisting tooling on the host is disproportionate and materially increases risk if the installed component or follow-on commands are compromised.

Content

Scanner excerpt · SKILL.md (reported line 90)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

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

These lines instruct the agent to direct users to the domestic Chinese site and explicitly say not to guide users using the international site unless the user clearly states they use it. This imposes a locale/site policy by default rather than offering the user a choice, which can violate language or locale neutrality requirements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.