Back to skill

Security audit

MiniMax Video Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently uses MiniMax's API to generate, query, and download videos, with expected network and credential use, but users should avoid sensitive prompts and choose download paths carefully.

Install only if you intend to use MiniMax and are comfortable sending prompts, image URLs, and generation metadata to MiniMax with your local API key. Do not provide confidential prompts or private/internal image URLs unless that is acceptable for your environment. When downloading, use a dedicated output directory and avoid paths that could overwrite important files.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/download.js:34
Finding

Arbitrary File Overwrite and Unrestricted Remote File Download

Content
View full analysis
{ const urlObj = new URL(url); const file = fs.createWriteStream(outputPath); const options = { hostname: urlObj.hostname, port: urlObj.port || 443, path: urlObj.pathname + urlObj.search, method: 'GET' }; console.log(`📥 开始下载: ${outputPath}`); const req = https.request(options, (res) => { if (res.statusCode >= 300 && res.statusCode < 400 && res.headers.location) { // 重定向,递归下载 file.close(); downloadFile(res.headers.location, outputPath).then(resolve).catch(reject); return; } res.pipe(file); file.on('finish', () => { file.close(); const stats = fs.statSync(outputPath); console.log(`✅ 下载完成! 大小: ${(stats.size / 1024 / 1024).toFixed(2)} MB`); resolve(); }); }); ``` ```js // scripts/download.js:109-128 async function downloadVideo(fileId, outputPath) { const apiKey = getApiKey(); // 确保输出目录存在 const dir = path.dirname(outputPath); if (!fs.existsSync(dir)) { fs.mkdirSync(dir, { recursive: true }); } // 先获取下载链接 console.log(`🔍 获取文件 ${fileId} 的下载链接...`); const url = `https://api.minimaxi.com/v1/files/retrieve?file_id=${fileId}`; const result = await httpGet(url, apiKey); if (result.file?.download_url) { console.log('📎 获取到下载链接,准备下载...'); await downloadFile(result.file.download_url, outputPath); return result.file; } else { console.error('❌ 获取下载链接失败:', result); process.exit(1 ...[truncated 3590 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (13)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code accesses credential material from the user's home directory and later uses it for an outbound network request. While the script's purpose is downloading a remote file, there is no user-facing disclosure that it will read stored credentials and transmit them to the MiniMax API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The script automatically reads a locally stored API key and transmits user-supplied prompts and image URLs to a third-party video-generation service without any explicit consent, warning, or data-handling notice. In an agent-skill context, this increases the risk of unintentional exfiltration of sensitive prompts, internal image URLs, or private media references to an external provider.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This code performs external network transmission to api.minimaxi.com as part of its core functionality. While not inherently malicious, in a security review of an agent skill it is a real data egress point: user prompts, selected model parameters, and referenced frame images are sent off-host, which can expose confidential or regulated content if used without clear boundaries.

Content

Scanner excerpt · scripts/generate.js (reported line 107)May include surrounding context.

js
// 生成视频
async function generateVideo(args) {
  const apiKey = getApiKey();
  const url = 'https://api.minimaxi.com/v1/video_generation';
  
  const payload = {
    prompt: args.prompt,

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 22)May include surrounding context.

md
// 查询任务状态
async function queryTask(taskId) {
  const apiKey = getApiKey();
  const url = `https://api.minimaxi.com/v1/query/video_generation?task_id=${taskId}`;

  console.log(`🔍 查询任务状态: ${taskId}`);

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 71)May include surrounding context.

md
// 查询任务状态
async function queryTask(taskId) {
  const apiKey = getApiKey();
  const url = `https://api.minimaxi.com/v1/query/video_generation?task_id=${taskId}`;

  console.log(`🔍 查询任务状态: ${taskId}`);

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 72)May include surrounding context.

md
// 查询任务状态
async function queryTask(taskId) {
  const apiKey = getApiKey();
  const url = `https://api.minimaxi.com/v1/query/video_generation?task_id=${taskId}`;

  console.log(`🔍 查询任务状态: ${taskId}`);

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 73)May include surrounding context.

md
// 查询任务状态
async function queryTask(taskId) {
  const apiKey = getApiKey();
  const url = `https://api.minimaxi.com/v1/query/video_generation?task_id=${taskId}`;

  console.log(`🔍 查询任务状态: ${taskId}`);

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 · scripts/download.js (reported line 130)May include surrounding context.

js
// 查询任务状态
async function queryTask(taskId) {
  const apiKey = getApiKey();
  const url = `https://api.minimaxi.com/v1/query/video_generation?task_id=${taskId}`;

  console.log(`🔍 查询任务状态: ${taskId}`);

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 · scripts/query.js (reported line 74)May include surrounding context.

js
// 查询任务状态
async function queryTask(taskId) {
  const apiKey = getApiKey();
  const url = `https://api.minimaxi.com/v1/query/video_generation?task_id=${taskId}`;

  console.log(`🔍 查询任务状态: ${taskId}`);

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The entire skill documentation is presented only in Chinese, and there is no indication that language choice is optional or that the skill is intentionally limited to a Chinese-speaking audience for a documented reason. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The markdown explicitly instructs users to run a download command with an output path, which affects local user data by writing a file to disk. While the command syntax shows the destination, there is no explicit warning or disclosure in the descriptive text that the skill will save content locally or may overwrite an existing file if the chosen path already exists.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script's docstring and all console messages are presented only in Chinese, which imposes a specific language on users without opt-in or documented locale scoping. This matches the language/locale policy violation category because no alternative language selection or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code file contains natural-language documentation and CLI output exclusively in Chinese, including usage instructions and error/help text. That forces a specific language on users without opt-in, which matches the locale-policy violation category for natural-language content.

Content

No source excerpt is available for this finding.