The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts and media URLs to generate video content, which represents a potential surface for indirect prompt injection.
Ingestion points: Untrusted data enters the agent context through the content array parameters (text, image_url, video_url, audio_url) in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore commands embedded within the user-provided prompt strings.
Capability inventory: The skill performs network operations via curl to send data to external API endpoints.
Sanitization: No input validation or sanitization of the user-provided text or URLs is explicitly documented in the skill instructions.
[EXTERNAL_DOWNLOADS]: The documentation references the mcp-minimax Python package and a hosted MCP server at minimax.mcp.acedata.cloud, which are official resources provided by the skill author.

minimax-video