MiniMax Music Generation

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:40 PM UTC
• Version: 1.1.0

Overview

This is a disclosed MiniMax music-generation skill that sends user prompts or lyrics to MiniMax and saves generated lyrics and audio locally.

Install only if you are comfortable sending prompts, lyrics, titles, and any reference-audio URLs to MiniMax using your API key. Avoid secrets, regulated data, or proprietary lyrics unless your MiniMax account and data-handling terms allow it; monitor API usage/costs; and delete generated local lyric/audio files when no longer needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Taint Tracking: Direct Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (11)

Tainted flow: 'audio_url' from os.getenv (line 177, credential/environment) → requests.get (network output)

Critical

• Category: Data Flow

Content

filename = f"{safe_title}_{timestamp}.mp3"
    filepath = os.path.join(save_dir, filename)

    response = requests.get(audio_url, timeout=60)
    with open(filepath, 'wb') as f:
        f.write(response.content)

• Confidence: 93% confidence
• Finding: response = requests.get(audio_url, timeout=60)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 95% confidence
• Finding: The skill performs network access, reads an API key from the environment, and writes files locally, but does not declare permissions. This creates a transparency and consent gap: a host system or user may treat the skill as lower-risk than it is, while it can still transmit user content to a third party and persist generated data on disk.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill states that lyrics and audio are automatically saved to local paths, but does not clearly warn users that generated content will persist on disk. This can expose sensitive prompts, private lyrics, or copyrighted material to other local users, backups, or later unintended reuse.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill description omits a clear privacy warning even though prompts and lyrics are sent to external MiniMax endpoints. Users may provide confidential or proprietary text believing processing is local, when it is actually transmitted to a third-party service.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The documentation shows user-provided prompts and lyrics being sent to a third-party API along with an API key, but it does not clearly disclose that potentially sensitive user content will leave the local environment. In an agent skill context, this can lead to unintended data exfiltration of user inputs or copyrighted/private lyrics because integrators may copy the example without adding consent, notice, or data-handling safeguards.

External Transmission

Medium

• Category: Data Exfiltration

Content

API_KEY = os.getenv("MINIMAX_API_KEY")

response = requests.post(
    "https://api.minimaxi.com/v1/lyrics_generation",
    headers={
        "Authorization": f"Bearer {API_KEY}",

• Confidence: 89% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

### 示例 2: 续写歌词

```python
response = requests.post(
    "https://api.minimaxi.com/v1/lyrics_generation",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={

• Confidence: 90% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

### 示例 3: 指定标题

```python
response = requests.post(
    "https://api.minimaxi.com/v1/lyrics_generation",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={

• Confidence: 87% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

API_KEY = os.getenv("MINIMAX_API_KEY")

response = requests.post(
    "https://api.minimaxi.com/v1/lyrics_generation",
    headers={
        "Authorization": f"Bearer {API_KEY}",

• Confidence: 89% confidence
• Finding: requests.post( "https://api.minimaxi.com/v1/lyrics_generation", headers={ "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" }, json=

External Transmission

Medium

• Category: Data Exfiltration

Content

### 示例 2: 续写歌词

```python
response = requests.post(
    "https://api.minimaxi.com/v1/lyrics_generation",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={

• Confidence: 90% confidence
• Finding: requests.post( "https://api.minimaxi.com/v1/lyrics_generation", headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}, json=

External Transmission

Medium

• Category: Data Exfiltration

Content

### 示例 3: 指定标题

```python
response = requests.post(
    "https://api.minimaxi.com/v1/lyrics_generation",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={

• Confidence: 87% confidence
• Finding: requests.post( "https://api.minimaxi.com/v1/lyrics_generation", headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}, json=

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.