minimax-multimodal-toolkit

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFEDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the mmx-cli tool using the command npm install -g mmx-cli to provide its core functionality.
  • [COMMAND_EXECUTION]: The skill relies on executing the mmx command-line utility for all AI operations, including generation and transcription tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as images, audio files, and text documents which are passed to LLMs and VLMs.
  • Ingestion points: Untrusted data is ingested via flags such as --messages-file, --image, --file, and --text-file in SKILL.md.
  • Boundary markers: No specific boundary markers or "ignore" instructions are used in the provided examples to prevent the model from following instructions embedded in the input data.
  • Capability inventory: The skill can read local files, write files to the system (e.g., via --out, --out-dir, or --download), and perform network API calls.
  • Sanitization: There is no evidence of sanitization or content filtering of the input files before they are processed by the tool.
  • [CREDENTIALS_UNSAFE]: The skill manages MiniMax API keys and OAuth tokens, persisting them to the local filesystem at ~/.mmx/config.json and ~/.mmx/credentials.json respectively.
  • [DATA_EXFILTRATION]: The skill supports sending data to external webhooks through the --callback-url flag in the video generate command and can fetch content from arbitrary URLs provided in the --image flag.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 10:27 AM