车辆过户信息查询(AI付版) - 聚合数据

• Outcome: Review
• Latest audit: Sep 16, 2026 · 10:01 AM UTC
• Version: 1.0.4

Overview

The skill’s paid VIN lookup behavior is mostly coherent, but its setup directs users toward an unpinned npm installer that can change what code runs and enables payment capability.

Review the installer step before use. Prefer a pinned, reviewed version of the Alipay payment dependency and run installation only in a least-privilege environment. Also confirm you are comfortable sending the VIN to Juhe and paying per query through the payment skill.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Error

• Location: SKILL.md:39

Finding

Execution of an Unpinned, Mutable npm Package

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 39-41
Vulnerability Type: Unsafe third-party dependency installation and execution
Risk Level: High

shell

npx -y @alipay/agent-payment@latest install

Technical Analysis

The Skill instructs the Agent to execute an npm package using the mutable latest tag. The package version and integrity are not pinned or independently verified. Consequently, the code executed by this command can change after the Skill has been reviewed.

The npx utility downloads and executes package code, while the -y option automatically accepts installation prompts. This reduces opportunities for the user or operator to inspect the resolved package version before execution. npm lifecycle scripts and the package CLI can execute arbitrary commands with the privileges of the Agent process.

This is an insecure supply-chain pattern. Compromise of the publisher account, npm package, release process, or registry resolution could turn the documented installation step into arbitrary local code execution.

Attack Path

1. The required Alipay dependency is absent or reported as unavailable.
2. The Agent follows the installation instruction in SKILL.md.
3. npm resolves @alipay/agent-payment@latest to whichever release currently owns the mutable tag.
4. An attacker who has compromised the package or its publication channel releases a malicious version and assigns it the latest tag.
5. npx -y downloads the malicious release and executes its lifecycle or CLI code without an interactive installation confirmation.
6. The malicious package executes commands under the operating-system account running the Agent.

Impact Assessment

Successful exploitation permits arbitrary code execution with the privileges of the Agent process. Depending on those privileges and the host configuration, an attacker could read or modify accessible files, access environment variables and ...[truncated 370 chars]

Remediation

View remediation

Remediation Suggestions

1. Replace the mutable latest tag with an exact, reviewed package version, such as @alipay/agent-payment@X.Y.Z.
2. Verify the package name, publisher identity, registry origin, and release provenance before installation.
3. Validate package integrity using an approved lockfile, npm integrity metadata, a trusted checksum, or signed provenance.
4. Remove -y so the resolved package and version can be reviewed before execution.
5. Require explicit user authorization immediately before downloading or executing the dependency.
6. Execute installation in a sandbox or least-privilege environment with restricted filesystem, credential, and network access.
7. Maintain an allowlist of approved dependency versions and require a new security review before updating the pinned version.
8. Where possible, install dependencies through a controlled deployment process rather than allowing runtime instructions to fetch and execute packages.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 90% confidence

Finding

The skill instructs installation via npx -y @alipay/agent-payment@latest, which pulls whatever package version is current at execution time. This creates a supply-chain risk: a compromised upstream release or unexpected breaking change could alter security behavior, payment flows, or dependency resolution without review.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 60% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 150)May include surrounding context.

向用户展示待查询的参数，严格遵守请求约束，向以下 URL 发起请求：

text

curl https://apis.juhe.cn/a2a/query \
  -d '{"resourceId":"807","data":{"vin":"<用户输入的VIN码>"},"isCharge":true}' \
  -H "Content-Type: application/json"