Back to skill

Security audit

Ozon-品牌Top榜 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent Ozon brand-ranking purpose, but it also directs broad host setup with unpinned package execution and persistent local tooling changes that users should review first.

Review this skill before installing. It appears intended for paid Ozon brand-ranking queries, but you should only let it install qhkit/Node from sources and versions you trust, avoid automatic @latest or unpinned npx execution where possible, and provide the API token only through a secret/environment mechanism you control.

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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says the skill 'must trigger' for similar requests, using broad language that can capture ambiguous user intents. Over-broad auto-activation can cause unintended external tool use, unnecessary paid API calls, and credentialed operations without sufficiently precise user intent matching.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The listed trigger phrase 品牌销量排行 is generic and could match ordinary discussion not specifically requesting this external data tool. In this skill's context, that raises the chance of accidental invocation of paid, networked functionality when a user may only be asking a general question.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill goes well beyond data-query guidance and directs the agent to install Node/qhkit, set persistent PATH changes, and configure API tokens on the host. For a skill whose purpose is querying Ozon ranking data, these host-modification and credential-handling steps increase attack surface and could expose secrets or alter the environment unnecessarily.

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 allows whatever package version is current at execution time to run on the host. That creates a supply-chain risk: a malicious or compromised upstream release could execute arbitrary code during installation or invocation.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

The duplicate finding points to the same persistence behavior: installing Node under the user's home directory and adjusting PATH for subsequent use. Even with checksum verification, this is still a persistent host modification unrelated to the minimal function of answering a brand-ranking query.

Content

Scanner excerpt · SKILL.md (reported line 101)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

The duplicate finding points to the same persistence behavior: installing Node under the user's home directory and adjusting PATH for subsequent use. Even with checksum verification, this is still a persistent host modification unrelated to the minimal function of answering a brand-ranking query.

Content

Scanner excerpt · SKILL.md (reported line 101)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.