Back to skill

Security audit

Ozon-品牌商品销售 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Ozon sales-data purpose is clear, but it also tells the agent to install runtime software and configure credentials on the user’s machine if dependencies are missing.

Review before installing. Use this skill only if you are comfortable letting it install or update Node/qhkit and store a Qinghu API token locally. Prefer a preinstalled, pinned qhkit version managed outside the skill, and confirm paid qhkit calls before allowing data queries.

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 (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says the skill '必须触发' when the user says the listed examples 'or提出同类需求', which leaves the activation boundary undefined. Without clear constraints or negative examples, similar everyday product-analysis requests could unintentionally invoke this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The standalone trigger phrase '品牌商品清单' is generic and could match many unrelated contexts, platforms, or data needs. The file does not pair it with exclusions or narrow activation conditions, increasing the chance of accidental invocation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill goes beyond describing how to query brand sales and instructs the agent to install software, modify configuration, and set API credentials in the host environment. That expands the skill's authority from data retrieval to system bootstrapping and secret handling, increasing the chance of unintended host changes or credential misuse.

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, which allows whatever package version is current at execution time to run in the host environment. That creates supply-chain and reproducibility risk, especially because this skill also encourages installation and execution on the user's machine.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Embedding fallback instructions to download and install Node.js binaries is unrelated to the narrow business purpose of querying Ozon brand-product data and materially increases system exposure. Even with checksum guidance, the skill is directing persistent software installation and PATH manipulation on the host, which is inappropriate for a data-query skill.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
93% confidence
Finding

This is a duplicate persistence pattern at the same line: the skill directs writing binaries into a user-controlled directory and altering the execution path, which leaves lasting environmental changes. In context, that is more dangerous because the skill is supposed to perform a narrowly scoped business query, not establish software on the host.

Content

Scanner excerpt · SKILL.md (reported line 93)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
93% confidence
Finding

This is a duplicate persistence pattern at the same line: the skill directs writing binaries into a user-controlled directory and altering the execution path, which leaves lasting environmental changes. In context, that is more dangerous because the skill is supposed to perform a narrowly scoped business query, not establish software on the host.

Content

Scanner excerpt · SKILL.md (reported line 93)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.