Hailuo Video Generator

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 9:07 AM UTC
• Version: 1.0.0

Overview

This skill is a straightforward MiniMax Hailuo video-generation helper that sends prompts and reference image URLs to MiniMax as part of its stated purpose.

Install only if you are comfortable sending your video prompt, reference image URLs, task metadata, and retrieval requests to MiniMax. Avoid sensitive personal, proprietary, or regulated content unless that external processing is intended, and keep the MiniMax API key out of shared files and logs.

A.I.G

Vulnerability Patterns

• 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
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

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

Findings (14)

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill clearly sends user prompts, image URLs, task IDs, and downloaded outputs to a third-party service, but the documentation does not prominently warn users that their content leaves the local platform and is processed by MiniMax. This creates a privacy and consent issue, especially if users provide sensitive prompts or private image references assuming local-only handling.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 44)May include surrounding context.

md

| 操作 | 方法 | 端点 |
|------|------|------|
| 生成视频 | POST | `https://api.minimax.chat/v1/video_generation` |
| 查询状态 | GET | `https://api.minimax.chat/v1/query/video_generation?task_id=xxx` |
| 下载视频 | GET | `https://api.minimax.chat/v1/files/retrieve?file_id=xxx` |

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 45)May include surrounding context.

md

| 操作 | 方法 | 端点 |
|------|------|------|
| 生成视频 | POST | `https://api.minimax.chat/v1/video_generation` |
| 查询状态 | GET | `https://api.minimax.chat/v1/query/video_generation?task_id=xxx` |
| 下载视频 | GET | `https://api.minimax.chat/v1/files/retrieve?file_id=xxx` |

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 46)May include surrounding context.

md

| 操作 | 方法 | 端点 |
|------|------|------|
| 生成视频 | POST | `https://api.minimax.chat/v1/video_generation` |
| 查询状态 | GET | `https://api.minimax.chat/v1/query/video_generation?task_id=xxx` |
| 下载视频 | GET | `https://api.minimax.chat/v1/files/retrieve?file_id=xxx` |

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 90)May include surrounding context.

md

| 操作 | 方法 | 端点 |
|------|------|------|
| 生成视频 | POST | `https://api.minimax.chat/v1/video_generation` |
| 查询状态 | GET | `https://api.minimax.chat/v1/query/video_generation?task_id=xxx` |
| 下载视频 | GET | `https://api.minimax.chat/v1/files/retrieve?file_id=xxx` |

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 120)May include surrounding context.

md

| 操作 | 方法 | 端点 |
|------|------|------|
| 生成视频 | POST | `https://api.minimax.chat/v1/video_generation` |
| 查询状态 | GET | `https://api.minimax.chat/v1/query/video_generation?task_id=xxx` |
| 下载视频 | GET | `https://api.minimax.chat/v1/files/retrieve?file_id=xxx` |

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 162)May include surrounding context.

md

| 操作 | 方法 | 端点 |
|------|------|------|
| 生成视频 | POST | `https://api.minimax.chat/v1/video_generation` |
| 查询状态 | GET | `https://api.minimax.chat/v1/query/video_generation?task_id=xxx` |
| 下载视频 | GET | `https://api.minimax.chat/v1/files/retrieve?file_id=xxx` |

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 169)May include surrounding context.

md

| 操作 | 方法 | 端点 |
|------|------|------|
| 生成视频 | POST | `https://api.minimax.chat/v1/video_generation` |
| 查询状态 | GET | `https://api.minimax.chat/v1/query/video_generation?task_id=xxx` |
| 下载视频 | GET | `https://api.minimax.chat/v1/files/retrieve?file_id=xxx` |

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 173)May include surrounding context.

md

| 操作 | 方法 | 端点 |
|------|------|------|
| 生成视频 | POST | `https://api.minimax.chat/v1/video_generation` |
| 查询状态 | GET | `https://api.minimax.chat/v1/query/video_generation?task_id=xxx` |
| 下载视频 | GET | `https://api.minimax.chat/v1/files/retrieve?file_id=xxx` |

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 93% confidence

Finding

This occurrence shows the actual API call target in the executable example that submits generation data off-platform. Because it uses externally hosted image URLs and prompt text, it can expose private content and associated metadata to MiniMax.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

bash

# 使用主体参考图生成视频
curl -s "https://api.minimax.chat/v1/video_generation" \
  -H "Authorization: Bearer $MINIMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 93% confidence

Finding

This occurrence shows the actual API call target in the executable example that submits generation data off-platform. Because it uses externally hosted image URLs and prompt text, it can expose private content and associated metadata to MiniMax.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

bash

# 使用主体参考图生成视频
curl -s "https://api.minimax.chat/v1/video_generation" \
  -H "Authorization: Bearer $MINIMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 93% confidence

Finding

This is the endpoint reference embedded in the executable generation example, which operationalizes transmission of user content to MiniMax. In context, the skill is specifically designed for off-platform generation, so the danger is not malicious exfiltration but insufficient informed consent and privacy framing.

Content

Scanner excerpt · SKILL.md (reported line 143)May include surrounding context.

bash

# 1. 生成视频
RESPONSE=$(curl -s "https://api.minimax.chat/v1/video_generation" \
  -H "Authorization: Bearer $MINIMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 93% confidence

Finding

This is the endpoint reference embedded in the executable generation example, which operationalizes transmission of user content to MiniMax. In context, the skill is specifically designed for off-platform generation, so the danger is not malicious exfiltration but insufficient informed consent and privacy framing.

Content

Scanner excerpt · SKILL.md (reported line 143)May include surrounding context.

bash

# 1. 生成视频
RESPONSE=$(curl -s "https://api.minimax.chat/v1/video_generation" \
  -H "Authorization: Bearer $MINIMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The manifest description is written entirely in Chinese, which can impose a specific language on users without any indication of opt-in or locale justification. The policy allows language constraints only when users are given a choice or the regional requirement is clearly documented.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.