Skills
skills/minimax-ai/skills/minimax-multimodal-toolkit/Gen Agent Trust Hub

minimax-multimodal-toolkit

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses system utilities including ffmpeg, ffprobe, curl, and jq for media format conversion, metadata extraction, and API communication.
  • [EXTERNAL_DOWNLOADS]: Downloads generated assets from official MiniMax domains (api.minimaxi.com and api.minimax.io) which are appropriate for the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill processes untrusted user input (prompts and lyrics) for AI generation, creating a surface for indirect prompt injection. 1. Ingestion points: --prompt, --lyrics, and --text arguments in scripts generate_image.sh, generate_video.sh, generate_voice.sh, and generate_music.sh. 2. Boundary markers: Data is structured within JSON payloads using jq. 3. Capability inventory: Network access via curl and file processing via ffmpeg. 4. Sanitization: JSON escaping is handled automatically by the jq utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 11:53 AM