The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install additional skills from third-party sources using npx skills add emilkowalski/skills and npx skills add heygen-com/hyperframes.
[COMMAND_EXECUTION]: The skill uses npx commands to install dependencies and perform rendering tasks, specifically npx hyperframes render.
[INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data that could contain malicious instructions.
Ingestion points: The skill reads content from brand.md, MOTION.md, and any files located within the ref/ directory to guide its output.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within these ingested files.
Capability inventory: The agent is empowered to generate and save HTML/JS code and execute shell commands (npx) for environment setup and rendering.
Sanitization: There is no mention of sanitizing, validating, or filtering the content of the ingested files before they are used to influence the agent's generation process.

apple-launch-film