minimax-cli-runtime

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the execution of the mmx CLI tool via shell commands, specifically mmx text chat --message "<prompt>". This pattern introduces a potential command injection surface if the underlying runtime implementation does not properly escape characters like backticks or dollar signs within the prompt.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the mmx-cli package from the NPM registry as a runtime dependency. This is documented as a standard setup procedure.
  • [PROMPT_INJECTION]: The skill performs operations like ask, review, and adversarial-review which process untrusted external data (prompts and code diffs). This represents an indirect prompt injection surface.
  • Ingestion points: External text provided to the ask and review commands.
  • Boundary markers: None identified in the provided documentation.
  • Capability inventory: Shell command execution via the mmx tool.
  • Sanitization: No specific sanitization or escaping mechanisms are described for the interpolated content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 03:40 AM
Security Audit — agent-trust-hub — minimax-cli-runtime