The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the hyperframes render command to process a JSON configuration file and generate a video output. This is the primary function of the skill and uses a specific configuration path (.hyperframes/temp_render_config.json).
[EXTERNAL_DOWNLOADS]: Uses the web_fetch tool to retrieve data from YouTube URLs and general web pages to extract transcripts and article content for video generation.
[DATA_EXPOSURE]: Reads local user files including PDFs, images, and HTML documents using the read_file tool to extract text and visual information for processing into a storyboard.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted content from external URLs and local files which could contain hidden instructions.
Ingestion points: web_fetch for YouTube/Web content and read_file for local documents and images in SKILL.md.
Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore or delimit potentially malicious instructions within the ingested content.
Capability inventory: The skill has shell execution capabilities via the hyperframes CLI and file system access for reading/writing configurations.
Sanitization: Absent; extracted text is directly mapped into the narrator_script and visual_content fields of the scene JSON.

generate-video