Security audit

laolei llm midi

Security checks for vulnerabilities and agentic risk

Overview

This is a simple MIDI-generation skill with no bundled code, persistence, credential access, or hidden authority.

Installers should expect a Chinese-first MIDI helper that may write local .mid outputs when asked. Review generated music files before importing them into other software, and use any optional online playback site only if you are comfortable opening that third-party service.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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 (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill content and invocation guidance are written primarily in Chinese and end with a direct instruction in Chinese to tell the assistant what music to generate. There is no explicit statement that users may interact in other languages or choose their preferred locale, which can violate a language-choice policy for general-purpose skills.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.