Veed Fabric
ReviewAudited by ClawScan on May 1, 2026.
Overview
This skill appears to do what it says, but it needs a fal.ai API key and will upload selected photos, audio, or scripts to fal.ai to generate videos.
Install only if you are comfortable sharing the chosen headshot, audio, and script with fal.ai. Keep FAL_KEY in your environment rather than chat, check fal.ai costs, and verify you have permission to upload any person’s image or voice.
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.
Your fal.ai key may be used to create jobs that consume credits or incur charges.
The skill uses a fal.ai account credential to submit generation and upload requests. This is expected for the integration, but it can access billable provider functionality.
**MUST** check that the `FAL_KEY` environment variable is set before doing anything else... **MUST NOT** proceed without a valid key.
Set FAL_KEY only in a trusted environment, do not paste the key into chat, and monitor fal.ai usage or billing.
Photos, voice recordings, and generated video URLs may leave your machine and be accessible through provider-hosted links.
The skill discloses that local images and audio are uploaded to an external CDN and become URL-accessible so fal.ai can process them.
When the user provides a local file path, upload it to fal.ai's CDN first... `FILE_URL` ... is now publicly accessible and can be used as `image_url` or `audio_url` in API calls.
Use only media you have rights and consent to upload, and avoid sensitive files unless you are comfortable with fal.ai handling them.
The agent may run local commands that read the file paths you provide and send those files to fal.ai.
The workflow relies on shell commands and curl calls to upload user-selected files and communicate with fal.ai. This is central to the stated purpose and is documented, but it is still local command/API activity.
UPLOAD_RESPONSE=$(curl -s -X POST "https://rest.fal.ai/storage/upload/initiate?storage_type=fal-cdn-v3" ...); curl -s -X PUT "$UPLOAD_URL" ... --data-binary @"/path/to/local/file.png"
Review the file paths before approving the workflow and provide only the specific image or audio files intended for the video.