AI Agentic Video Editor
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a coherent video-editing integration that uses a declared API key and remote editing service, with appropriate warnings to confirm mutating edits before running them.
Before installing, confirm you trust the Levea/Livecore service with the videos you plan to edit. Use a dedicated API key, preview outputs before publishing, and require plan approval for destructive or high-stakes edits.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
64/64 vendors flagged this skill as clean.
Risk analysis
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 skill may change or export video projects, so users should review the planned edits before allowing execution.
The skill can perform mutating video edits, but it also clearly instructs the agent to obtain confirmation and use a planning-approval flow for irreversible actions.
Before executing any mutating edit on user content, describe the planned edit and request explicit confirmation from the user. For destructive or irreversible workflows, pass `requirePlanApproval: true`
Use the confirmation flow for all content-changing edits and enable `requirePlanApproval: true` for high-stakes, destructive, or hard-to-undo edits.
The API key may allow the skill to access and modify projects in the connected video-editing account.
The skill requires a bearer API key for the video-editing provider, which is expected for this integration and is declared in the metadata.
Auth: `Authorization: Bearer {ADSCENE_API_KEY}`Use a dedicated, least-privileged API key if available, keep it private, and rotate it if you suspect exposure.
Private videos, faces, speech transcripts, and visual text may be processed by the external video-editing service.
The skill sends or accesses video project content through a remote provider API for analysis and editing, including potentially sensitive faces, transcripts, and on-screen text.
Run computer-vision analysis on frames (object, face, scene) ... Search the transcript by keyword, semantic meaning, or timestamp window ... Cross-asset face identity search
Avoid using sensitive or confidential footage unless you trust the provider and understand its data handling terms.