skills/minimax-ai/cli/mmx-h3-video/Gen Agent Trust Hub

mmx-h3-video

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the MiniMax-H3 API through shell commands using the mmx CLI. It provides specific instructions for building a local artifact (bun run build) and executing the resulting JavaScript file (node ./dist/mmx.mjs) to perform generation and configuration tasks.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection through its command construction methods.
  • Ingestion points: User-supplied text is interpolated into the --prompt argument of shell commands described in SKILL.md.
  • Boundary markers: The skill's examples utilize double quotes to encapsulate the prompt (e.g., --prompt "<video prompt>"), which does not protect against shell metacharacters such as backticks or subshells.
  • Capability inventory: The agent is authorized to execute shell commands via the mmx and node runtimes.
  • Sanitization: There are no explicit instructions within the skill to sanitize, escape, or validate user-provided strings for shell-active characters prior to execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 05:02 AM
Security Audit — agent-trust-hub — mmx-h3-video