The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several command-line tools for its primary functionality: npx hyperframes (HeyGen HyperFrames CLI) to render HTML compositions, ffmpeg for video muxing, and python3 to run internal audio processing scripts (mix.py and build.py). These are standard operations for the stated purpose of video generation.
[EXTERNAL_DOWNLOADS]: The HTML animation template (reference/index.template.html) loads the GSAP (GreenSock Animation Platform) library from the well-known JSDelivr CDN (https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js).
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted brand assets (site CSS, SVGs, logos, and music files) to generate the video, but the risk is limited by the media-focused processing pipeline.
Ingestion points: reference/build.py ingests SVG vectors and PNG logos; reference/mix.py ingests user-provided MP3 files; SKILL.md instructs the agent to read CSS from live sites.
Boundary markers: No specific delimiters or warnings are used to isolate untrusted asset content.
Capability inventory: The skill executes shell commands via npx hyperframes, ffmpeg, and Python scripts (reference/build.py, reference/mix.py).
Sanitization: The skill does not perform explicit sanitization or validation of the ingested SVG code or CSS before processing.

launch-video