minimax-music

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted content from user-provided lyrics, style prompts, and external audio URLs.
  • Ingestion points: External data enters the context via the lyrics, prompt, and audio_url parameters defined in the MiniMax API request structures within SKILL.md.
  • Boundary markers: The skill does not specify the use of clear delimiters or instructions to ignore embedded commands within the input data, although it does use structure tags for lyrics such as [Intro] and [Chorus].
  • Capability inventory: The skill involves network operations (POST requests to api.minimax.io) and file system writes (saving audio artifacts to local project directories like projects/<project-id>/assets/music/).
  • Sanitization: The instructions do not include specific sanitization or validation steps for the agent to perform on external inputs before transmission to the API, relying on the provider's moderation (e.g., error code 1026).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:42 PM