Kami Video
ReviewAudited by ClawScan on May 11, 2026.
Overview
Kami Video is a coherent cloud video-editing skill, but users should know it uses a Nemo Video token and sends selected media to a third-party rendering API.
This appears purpose-aligned for cloud video editing. Before installing, be comfortable with Nemo Video receiving your selected footage and prompts, protect the NEMO_TOKEN, and avoid uploading sensitive videos unless you trust the provider's data handling.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Anyone using the skill should understand that the token authorizes video-editing requests and may be tied to credits or session history.
The skill requires a provider token for all API calls. This is expected for a cloud video service, but it is still account/session authority.
Every API call needs `Authorization: Bearer <NEMO_TOKEN>`
Use a token intended for this service only, avoid sharing logs that may contain credentials, and revoke or rotate the token if it is exposed.
Private or copyrighted video footage may be uploaded to Nemo Video's cloud systems for editing and rendering.
The workflow sends user-selected media and prompts to an external provider for processing. This is central to the skill's purpose, but it is a sensitive data transfer.
This tool takes your raw video footage and runs AI video editing through a cloud rendering pipeline. You upload, describe what you want, and download the result.
Only upload files you are comfortable sending to the provider, and review the provider's privacy and retention terms for sensitive media.
The skill may contact the Nemo Video API and create a session even before a specific edit is requested.
The skill instructs the agent to automatically create/connect a provider session. This is disclosed setup behavior and fits the video-editing purpose, but it initiates external API activity early.
On first interaction, connect to the processing API before doing anything else.
Install it only if you are comfortable with automatic provider connection when invoking the skill; ask for confirmation before uploads or exports if the footage is sensitive.