wanjie-openclaw-video

Generate high-performance Veo videos from natural language prompts with automatic dependency handling, timeout recovery, and continuous background monitoring.

Things to consider before installing: - This skill will read ~/.openclaw/openclaw.json and use the apiKey it finds there to call https://maas-openapi.wanjiedata.com. If you don't want the skill to have access to that key, do not install it or inspect/modify the code to accept an explicit, limited key. - The manifest does not declare the required config path or credential, but the code uses it — ask the author to declare required config paths or change to use a named env var so you can control which key is used. - The skill can auto-install Python packages at runtime (requests) and spawns detached background Python processes. If you prefer to control installs and processes, review and run the code manually in a sandboxed environment first. - The worker opens the first URL returned by the remote service in your browser automatically. That URL may be attacker-controlled if the remote service is compromised; consider disabling automatic opening or inspect the returned URL before clicking. - SKILL.md claims a Windows scheduled task will be created; no code does that. Confirm with the author whether additional install steps are needed or whether documentation is stale. - If you decide to proceed, run the skill in an isolated environment (VM/container/user account) and audit ~/.openclaw/openclaw.json contents and permissions. Ask the developer to (a) explicitly declare required config paths/credentials in the manifest, (b) avoid automatically opening external URLs, and (c) provide a reproducible installation mechanism for any background scheduler they claim to create.

Type: OpenClaw Skill Name: wanjie-openclaw-video-v1-0-0 Version: 1.0.0 The skill exhibits high-risk behaviors including reading the global `openclaw.json` configuration file to extract API keys and automatically installing Python dependencies via `pip` (`video_interface.py`). It also claims to implement persistence via a Windows Task Scheduler entry (`OpenClaw_Veo_Monitor`) and automatically opens URLs parsed from API responses in the system browser (`veo_worker.py`). While these features are aligned with the stated goal of an automated video generator, the combination of credential access, background persistence, and automated execution is highly intrusive and exceeds the typical scope of a simple skill.