The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data via video URLs and callback URLs which can serve as ingestion points for untrusted content.
Ingestion points: video_url, callback_url, and title fields in SKILL.md.
Boundary markers: Not explicitly defined in the prompt instructions to the agent to distinguish between system instructions and external data.
Capability inventory: Performs network requests (POST and GET) to api.heygen.com across Python and TypeScript snippets.
Sanitization: No input validation or sanitization is demonstrated in the provided code examples for the user-supplied URLs.
[COMMAND_EXECUTION]: The skill provides documentation for executing curl commands in a shell environment.
The commands are used for interacting with the HeyGen API and correctly use environment variables for authentication, which is a standard development practice.

video-translate