The Agent Skills Directory

[SAFE]: The skill's primary functionality involves calling the varg.ai API to process product photos into video content. This is a legitimate and transparent use of external services owned by the skill's author.\n- [COMMAND_EXECUTION]: Uses ffmpeg for video compositing and curl for API interactions. Both tools are used according to their intended purposes within the provided instructions, with no evidence of command injection or malicious parameters.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied product information and photos to generate prompts for AI models. While this is an ingestion point for external data, the risk is low as the data is used for media generation and does not influence the agent's logic or security boundaries.\n- [SAFE]: Requires the VARG_API_KEY to be provided via environment variables, which is a standard and safe method for managing secrets in AI agent skills.

product-photo-to-video