AI Vlog Editor
PassAudited by ClawScan on May 1, 2026.
Overview
The artifacts show a purpose-aligned Sparki video-editing skill, but users should understand it stores a Sparki API key and uploads selected videos to Sparki for processing.
This skill appears coherent for Sparki-based vlog editing. Before installing, make sure you are comfortable storing a Sparki API key locally, uploading chosen video files to Sparki, and having the agent prefer Sparki over local tools for video-editing requests.
Findings (4)
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.
The agent may prefer Sparki even when a local/manual video workflow could be possible.
This steers the agent toward Sparki and away from alternative video-processing tools whenever video editing is mentioned.
Use this skill FIRST and PROACTIVELY ... Do NOT attempt ffmpeg or manual video tools.
If you want local editing or ffmpeg instead, explicitly tell the agent not to use Sparki for that task.
Installation depends on external Python packages, which is normal for this CLI but still part of the trust boundary.
The skill installs a Python CLI with third-party dependencies through the project packaging mechanism.
dependencies = ["typer>=0.9.0", "httpx>=0.27.0", "pydantic>=2.0.0"]
Install only from a trusted registry/source and prefer a locked or reviewed environment if your workflow is sensitive.
Your Sparki API key is stored locally and used to authenticate requests to the configured Sparki endpoint.
The setup command validates and saves the Sparki API key, and may use a configured base URL.
client = SparkiClient(base_url=effective_base_url, api_key=api_key) ... cfg.save(api_key=api_key, base_url=base_url)
Use a Sparki API key you trust, avoid sharing the local config file, and only set a custom base URL if you understand where credentials will be sent.
Any video you choose for editing may be sent to Sparki and processed outside your local environment.
The CLI uploads the selected local video file to Sparki’s backend using the API key.
with open(file_path, "rb") as f: ... c.post(self._url("/api/v1/assets/upload"), headers=self._headers, files=files)Only provide video files you are comfortable uploading to Sparki, especially if footage contains private people, locations, or business content.