minimax-video

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides curl command examples to interact with the MiniMax video generation and task management APIs.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with external endpoints api.acedata.cloud and cdn.acedata.cloud. These are vendor-owned resources associated with the skill author, representing normal functionality.
  • [PROMPT_INJECTION]: The skill processes user-supplied text and media URLs to generate video content, creating a surface for indirect prompt injection.
  • Ingestion points: text, image_url, video_url, and audio_url fields within the content array in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate user-provided content from agent instructions.
  • Capability inventory: Performs network POST requests to an external API via curl.
  • Sanitization: No explicit sanitization or validation of the input URLs or text content is described in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:33 PM
Security Audit — agent-trust-hub — minimax-video