Back to skill

Security audit

Shopee-品牌价格分布 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Shopee brand price-distribution helper, but users should review its qhkit installation and token setup steps before use.

Install only if you are comfortable letting the agent install or update Node/qhkit and configure a qhkit API token. Prefer a preinstalled, pinned qhkit version when possible, and confirm the quoted Qinghu credit cost before any paid call.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
94% confidence
Finding

The manifest description and trigger section state that the skill "must" trigger when the user says "品牌定价策略", but that phrase is generic and could refer to broad pricing-strategy analysis rather than this narrow Shopee price-band lookup. The file does not provide exclusion conditions or negative examples to constrain when this skill should not activate.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This skill goes far beyond a simple brand price-distribution query by directing the agent to install Node, install global packages, modify PATH, and set API credentials in the host environment. Those actions materially expand the attack surface and create opportunities for persistence, credential exposure, and unintended system modification unrelated to the core user task.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The skill instructs fallback execution via npx @iqinghu/qhkit without pinning a specific version. That allows whatever package version is current at execution time to run, increasing supply-chain risk and making behavior non-deterministic in a skill that also requests installation and credential setup on the host.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
95% confidence
Finding

This duplicate finding captures the same persistence behavior: unpacking executables into the user's home directory and altering PATH for subsequent command resolution. For a narrowly scoped analytics skill, modifying the host in this way is disproportionate and creates lingering trust and integrity risks.

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
95% confidence
Finding

This duplicate finding captures the same persistence behavior: unpacking executables into the user's home directory and altering PATH for subsequent command resolution. For a narrowly scoped analytics skill, modifying the host in this way is disproportionate and creates lingering trust and integrity risks.

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

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

All user-facing instructions, trigger phrases, and operational guidance are written exclusively in Chinese, and the skill does not indicate that users may choose another language. Under the policy, language constraints should be optional or explicitly justified with user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.