The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches external resources from remotionui.com to function, including component metadata (components.json), detailed guides (remotionui-agent.md), and a registry index (index.json).
[COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands using npx remotion-ui for project initialization, component installation, and environment diagnostics. It also uses npm run dev for local development.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes external content that could contain malicious instructions.
Ingestion points: Data is ingested from remotionui.com/ai/components.json and remotionui.com/ai/remotionui-agent.md as specified in the 'Agent indexes' section of SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or sanitize embedded instructions within the fetched external data.
Capability inventory: The skill possesses the ability to execute shell commands (via npx and npm) and manage local files within the user's repository.
Sanitization: No sanitization or validation logic is described for the external content before it is processed by the agent.

remotionui-agent