OpenClaw AI Video Editor

PassAudited by ClawScan on May 17, 2026.

Overview

This is a disclosed API-backed video editing skill that uses a Levea/OpenClaw API key to edit and export videos, with no artifact evidence of hidden exfiltration or malicious behavior.

Install only if you intend to use the Levea/OpenClaw video-editing API. Configure the API key and URL carefully, approve plans before mutating important projects, preview every export before publishing, and avoid reusing workingMemory across unrelated videos.

Findings (5)

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.

What this means

If approved, the agent can change a video project and export results; mistakes could require reverting or re-editing.

Why it was flagged

The skill can perform mutating video edits, but the artifact explicitly requires confirmation before non-read operations.

Skill content
Before executing any mutating edit on user content (anything beyond `read_*` / `query_*`), describe the planned edit and request explicit confirmation from the user.
Recommendation

Preview outputs before sharing and use `requirePlanApproval: true` for important, destructive, or hard-to-reverse edits.

What this means

The configured API key may grant access to the user's video-editing account or projects on the provider service.

Why it was flagged

The skill uses a provider API key from the environment to authenticate network requests, which is expected for this API-backed editor.

Skill content
'Authorization': `Bearer ${process.env.ADSCENE_API_KEY}`
Recommendation

Use a least-privilege API key if available, store it securely, and ensure `ADSCENE_API_URL` points only to the intended provider endpoint.

What this means

Installing the skill makes its packaged code available to run when the tool is invoked.

Why it was flagged

The skill is not only instructions; it includes executable runtime JavaScript packaged as an OpenClaw runtime extension.

Skill content
"runtimeExtensions": [
      "dist/index.js"
    ]
Recommendation

Install from the expected package/source and review updates, especially because the registry summary under-declares the runtime and environment requirements.

What this means

Reusing the wrong workingMemory could resume an old or unintended edit plan.

Why it was flagged

The workflow can carry planning state across calls, which is useful for approvals but can also carry stale or untrusted context.

Skill content
`workingMemory` — durable working-memory snapshot. Re-send to resume after `awaiting_approval`
Recommendation

Only reuse workingMemory from the same trusted project/session, and start fresh when switching videos or workflows.

What this means

A user who configures the wrong provider URL could send video data or an API key to an unintended endpoint.

Why it was flagged

The documentation references provider domains and account/key setup; users should verify these domains before entering credentials.

Skill content
Use `https://api.livecore.ai` for `ADSCENE_API_URL`; Studio is only for signup, login, and key management.
Recommendation

Confirm the official provider domains independently before creating keys or setting `ADSCENE_API_URL`.