The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx -y hyperframes@latest to download and execute the HyperFrames project initializer from the npm registry. It also loads the GSAP animation library from the jsDelivr CDN within the generated HTML templates.
[COMMAND_EXECUTION]: The skill executes several shell commands including node, ffmpeg, and npx hyperframes (for linting and rendering). These are standard operations for building and processing video assets.
[DATA_EXFILTRATION]: The skill reads local project files such as .agents/product-marketing-context.md, brand-kit.json, and Tailwind configurations. This data is used solely to generate on-brand video content and is not sent to unauthorized external domains.
[PROMPT_INJECTION]: This skill is susceptible to indirect prompt injection as it processes untrusted data from external websites via WebFetch to generate video scripts.
Ingestion points: Web content fetched in Step 1c and local marketing files read in Step 1a.
Boundary markers: Absent; the skill does not use specific delimiters to isolate external content from its internal instructions.
Capability inventory: The skill can execute shell commands (npx), write files, and perform network requests.
Sanitization: No explicit sanitization or filtering of the fetched content is described before it is used to influence script generation.

tiktok-launch-video