Adscene Video Editor

ReviewAudited by ClawScan on May 14, 2026.

Overview

This looks like a remote video-editing API skill, but its included README describes a different background-replacement skill and references missing code, so it needs review before use.

Review this skill before installing. Verify that the publisher fixes the README/SKILL mismatch and supplies any referenced code, do not fetch a missing handler.ts from an untrusted location, use a restricted API key, and test broad autonomous edits on non-critical video projects first.

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

A user could believe they are installing a narrow chroma-key/background tool when the active skill instructions expose broad video editing and export capabilities.

Why it was flagged

This README presents the package as a background-replacement skill, while SKILL.md presents a much broader autonomous video editor. The mismatch can mislead users about the scope of actions the skill may perform.

Skill content
# OpenClaw Background Replacement Skill

This OpenClaw skill enables AI agents to remove and replace video backgrounds
Recommendation

Reconcile the README, skill name, endpoints, and advertised capabilities before installation; users should verify the actual SKILL.md behavior rather than relying on the README.

What this means

Installation instructions may fail or cause users to source and run code that was not included in the reviewed artifacts.

Why it was flagged

The README instructs users to copy a handler.ts file and install a dependency, but the provided manifest contains no handler.ts and the registry says there is no install spec or code files. Following these docs could push users toward unreviewed missing code.

Skill content
cp handler.ts ~/.openclaw/skills/background-replacement/
...
npm install axios
Recommendation

Publish a complete, consistent package or remove stale handler/dependency instructions; do not fetch or add a missing handler.ts from an untrusted source.

What this means

A vague prompt could result in multiple edits to a project, including deleting or replacing layers or generating exports.

Why it was flagged

The skill intentionally gives one free-form tool authority to perform multi-step editing actions, including project mutation and export. This is purpose-aligned for a video editor, but broad.

Skill content
Pass a natural-language description in `params.prompt`... plans a DAG of canonical actions, executes through the safety gates... Insert / update / replace / delete layers... `EXPORT_VIDEO`
Recommendation

Use explicit prompts, test on copies of projects, and require user confirmation for destructive edits or final exports where possible.

What this means

Anyone with the key may be able to access or modify video projects allowed by that API credential.

Why it was flagged

The skill uses a bearer API key to authenticate to the configured Adscene API. This is expected for the integration, but it is sensitive authority.

Skill content
Auth: `Authorization: Bearer {ADSCENE_API_KEY}`
Recommendation

Use a least-privilege API key, keep it in environment configuration only, and rotate it if exposed.

What this means

Video project details and editing instructions may be processed by the configured service.

Why it was flagged

Prompts, project identifiers, and optional scene data are sent to a configured remote API endpoint. This is disclosed and purpose-aligned, but it involves project data leaving the local agent.

Skill content
POST {ADSCENE_API_URL}/api/v1/misc/openclaw/v1/execute ... "params": { ... }, "project_id": "optional-project-id", "scene": { ... }
Recommendation

Set ADSCENE_API_URL only to a trusted endpoint and avoid sending confidential project data unless the provider’s handling is acceptable.