Emergence Video Producer
PassAudited by ClawScan on May 10, 2026.
Overview
This appears to be a coherent video-production skill, but it depends on external media/browser/TTS tools and may send narration text to a provider.
Before installing or using this skill, make sure you trust the local WebReel, FFmpeg, Edge-TTS/DashScope, and Pillow installations. Review the storyboard, target URL, generated WebReel/Slidev files, and narration text before production, and avoid recording private sites or sending confidential text to TTS providers.
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 could record the selected website or content and create media files from it.
The skill intentionally uses browser automation and local media tools. That is expected for its purpose, but users should review target URLs, generated configs, and output paths before allowing production runs.
The agent executes the headless recording and assembly. It handles: - Browser automation (WebReel) - Slide rendering (Slidev) - Frame extraction and FFmpeg merging
Use it only with URLs/content you intend to record, and review the storyboard and generated configuration before running production.
Behavior and security partly depend on the local versions of WebReel, FFmpeg, Edge-TTS, DashScope tooling, and Pillow.
The skill relies on external tools and libraries, but the provided install metadata does not pin or install them. This is expected for an instruction-oriented media workflow, but users must trust and manage those dependencies themselves.
Ensure the following tools are in the path: - `webreel` (for browser recording) - `ffmpeg` (for assembly) - `edge-tts` or `dashscope` credentials (for narration) - `Pillow`
Install dependencies from trusted sources, prefer pinned versions, and verify which binaries are on PATH before use.
If DashScope credentials are provided, the agent may be able to use that account for narration generation.
The skill may use provider credentials for narration. This is purpose-aligned, and the artifacts do not show hardcoded credentials or credential logging.
`edge-tts` or `dashscope` credentials (for narration)
Use least-privilege provider credentials and avoid placing unrelated secrets in the working directory or environment.
Any sensitive information placed in narration text may be sent to the TTS provider.
Narration text is passed to an external TTS command/provider. This is disclosed and central to the skill, but it is still a data flow outside the local script.
"edge-tts", "--text", text, "--write-media", output_file, "--voice", voice
Review narration text before generation and do not include passwords, private customer data, unreleased business information, or other secrets unless the provider is approved for that data.