Back to skill

Security audit

minimaxmusic

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MiniMax music-generation guide with expected external API use and no hidden install, persistence, or local access behavior.

Install only if you are comfortable sending music prompts and any provided lyrics to MiniMax. Avoid confidential, personal, proprietary, or unlicensed copyrighted text, and store any MiniMax API key securely outside the skill text or shared scripts.

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
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill sends user-provided prompts and potentially full song lyrics to a third-party API, but the description does not warn users that their content leaves the local environment. This creates a privacy and compliance risk because users may submit copyrighted, confidential, or sensitive text without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This skill is explicitly designed to transmit user content to an external MiniMax endpoint, which means prompts and lyrics are shared outside the host system. In this context the network transmission is expected functionality, but it still carries data exposure risk if users are not warned or if sensitive content is included.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

API 端点

text
POST https://api.minimaxi.com/v1/music_generation

请求格式 (PowerShell)

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The PowerShell example performs a direct POST of user-controlled JSON, including lyrics, to an external API using bearer authentication. Although necessary for the feature, this creates a clear outbound data flow that can expose sensitive or proprietary user input to a third party.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

lyrics = "歌词内容" # 仅非纯音乐时需要 } | ConvertTo-Json -Compress

Invoke-RestMethod -Uri "https://api.minimaxi.com/v1/music_generation" -Method Post -Headers @{ Authorization = "Bearer <API_KEY>" } -ContentType "application/json" -Body ([System.Text.Encoding]::UTF8.GetBytes($json)) -TimeoutSec 180

text

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

All user-facing natural-language instructions and descriptions in the skill are presented only in Chinese, which effectively forces a specific language without any opt-in or explanation. The policy allows locale constraints when they are clearly documented and justified, but no such justification appears here.

Content

No source excerpt is available for this finding.