ClawHub
Back to skill

Security audit

MiniMax Lyrics Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it sends lyric prompts to MiniMax to generate structured song lyrics, with no hidden persistence or destructive behavior found.

Install only if you are comfortable storing a MiniMax API key locally and sending lyric prompts, titles, and any existing lyrics you provide to MiniMax. Avoid using it for confidential or proprietary text unless MiniMax's data handling terms are acceptable to you.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: minimax-lyrics
description: Generate song lyrics with structure tags using MiniMax lyrics_generation API. Use when user asks to write lyrics, generate a song, or create a song. Triggers on: "帮我写歌词", "生成歌词", "写首歌词", "generate lyrics", "song lyrics".
---

# MiniMax Lyrics Generation

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad and overlap with common user requests such as 'generate lyrics' or 'create a song', which can cause the skill to activate when the user did not explicitly intend to use this specific integration. Unintended activation can lead to unnecessary external API use, unexpected disclosure of user prompts to a third party, and confusing agent behavior.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The function claims to read an API key from this skill's own configuration, but instead hard-codes a path to another skill's config under ~/.openclaw/workspace/skills/minimax-lyrics/lyrics_config.json. This creates a cross-skill secret dependency that can cause unauthorized use of another skill's credentials, unexpected data flow, and confused-deputy behavior if this script is reused in a different context.

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 · scripts/generate_lyrics.py (reported line 31)May include surrounding context.

python
"""Generate lyrics via MiniMax API. Returns dict with song_title, style_tags, lyrics."""
    import urllib.request

    url = "https://api.minimaxi.com/v1/lyrics_generation"
    payload = {
        "mode": mode,
        "prompt": prompt,

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script transmits user-supplied prompts and optional existing lyrics to a third-party API, but it does not provide an explicit warning or consent mechanism at the point of use. If users paste sensitive or proprietary text into the prompt or lyrics fields, that data will be sent off-host without clear disclosure, creating a privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
66% confidence
Finding

The trigger description hard-codes both Chinese and English trigger phrases, while the rest of the document largely uses Chinese parameter descriptions and examples. This may implicitly steer usage toward specific languages without stating that the user can choose their preferred language or output locale.

Content

No source excerpt is available for this finding.