The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or unauthorized data access methods were identified. The skill focuses entirely on its stated purpose of video generation and editing using the provided Hyper MCP tools.
[PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it processes user-provided prompts and analyzes video content. However, this is inherent to the functional requirements of video generation and analysis.
Ingestion points: User-provided prompts in generate_video, text for overlay_text, and video files processed by analyze_video (SKILL.md).
Boundary markers: No explicit use of delimiters (e.g., XML tags or block markers) for user content is specified in the prompt templates.
Capability inventory: The skill utilizes tools for file generation, modification, analysis, and deletion within the MCP environment (SKILL.md).
Sanitization: There is no evidence of specific input sanitization or validation of the text or visual content before it is passed to the underlying AI models.

video-generation