The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill identifies the HEYGEN_API_KEY as a required environment variable and explicitly documents secure authentication patterns. No hardcoded keys, tokens, or secrets were found in the instructions or reference files.
[EXTERNAL_DOWNLOADS]: All external references and download links point to official HeyGen domains (e.g., heygen.com, heygen.ai) or well-known developer resources (e.g., GitHub, npm). These are verified services essential for the skill's operation.
[DATA_EXFILTRATION]: The skill describes methods for uploading local assets (images, audio, video) to HeyGen's official infrastructure. This is a core functional requirement of the video generation service and is implemented via standard, documented API calls.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text to generate video scripts and AI prompts. While this represents a data ingestion surface, it is the primary intended use case of the skill, and the provided 'prompt-optimizer' guidelines help ensure inputs are structured safely.

heygen