Back to skill

Security audit

Ozon-商品详情 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Ozon product-data lookup that uses a paid qhkit API/CLI, with setup and credential handling that users should review before use.

Install only if you are comfortable using the qhkit npm package, configuring a Qinghu token, and spending Qinghu credits after approval. Prefer a preinstalled or pinned qhkit version when possible, and review any proposed Node/npm setup before allowing it.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
96% confidence
Finding

The metadata says the skill 'must trigger' for broadly similar requests, which can cause over-invocation on ambiguous prompts. In context, this is risky because invocation can lead to paid tool usage and local setup actions, so an overly broad trigger increases the chance of unintended execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The phrase '这个商品卖了多少' is broad natural language that could occur in many contexts and does not itself constrain platform, data source, or required product-ID lookup. The trigger section provides no negative examples or guardrails to distinguish intended Ozon-specific use from general discussion.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

For a product-detail lookup skill, the documentation goes far beyond minimal execution and instructs installing Node, globally installing packages, setting tokens, modifying PATH, and changing persistent local configuration. This expands the attack surface significantly and could lead an agent to make unnecessary system changes or handle secrets on the user's machine for a simple data query.

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 version, which makes execution depend on whatever package version is current at runtime. That creates supply-chain and reproducibility risk: a later compromised or incompatible release could be fetched and executed in the user's environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This duplicate finding identifies the same persistent installation behavior: writing binaries under the user's home directory and altering PATH. Such actions exceed the least-privilege needs of the stated skill and can leave long-lived modifications that survive the immediate task.

Content

Scanner excerpt · SKILL.md (reported line 91)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 duplicate finding identifies the same persistent installation behavior: writing binaries under the user's home directory and altering PATH. Such actions exceed the least-privilege needs of the stated skill and can leave long-lived modifications that survive the immediate task.

Content

Scanner excerpt · SKILL.md (reported line 91)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
83% confidence
Finding

The instructions mandate use of the domestic iqinghu.com site and explicitly tell the agent not to guide users toward the international site unless the user clearly states that preference. This imposes a locale/site choice by default without offering the user a language or locale option.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.