The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill makes requests to api.acedata.cloud for video generation and status polling. These network operations target the official infrastructure of the skill author (acedatacloud).
[CREDENTIALS_UNSAFE]: Adheres to security best practices by instructing the user to store the ACEDATACLOUD_API_TOKEN in a .env file rather than hardcoding it within scripts or instructions.
[PROMPT_INJECTION]: As the skill processes user-supplied text prompts and external image URLs to generate video, it possesses an inherent surface for indirect prompt injection.
Ingestion points: prompt, image_url, and reference_image_urls parameters defined in SKILL.md.
Boundary markers: None present; the skill does not define specific delimiters to isolate external data from instructions.
Capability inventory: The agent uses curl to transmit data to the external AceDataCloud API.
Sanitization: The instructions do not specify any validation or sanitization of the input strings or URLs before they are processed.

grok-video