Wan 22
v1.0.0Drop a text prompt or reference image and watch WAN 2.2 bring it to life as a fluid, cinematic video clip. This skill taps into the wan-22 model to generate...
⭐ 0· 43·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description (WAN 2.2 video generation) aligns with requested capability: NEMO_TOKEN is the single declared credential and all runtime actions target the nemovideo.ai inference/rendering backend. No unrelated credentials, binaries, or install steps are requested.
Instruction Scope
SKILL.md instructs network calls to nemovideo.ai for anonymous-token issuance (if NEMO_TOKEN not present), session creation, SSE generation, uploads, and export polling — all consistent with a cloud video service. It also instructs uploading local files (multipart files=@/path) and detecting the agent install path to set an attribution header, which means the agent will read local files and a filesystem path and transmit them externally. This behavior is expected for image-to-video workflows but is important for privacy: user files and environment-detected install paths will be sent to the remote service.
Install Mechanism
Instruction-only skill with no install spec and no downloadable artifacts — lowest-risk installation footprint. Nothing is written to disk by an installer in the skill package itself.
Credentials
Only a single environment variable (NEMO_TOKEN) is declared as required. The instructions accommodate creating a short-lived anonymous token if none is provided. There are no unrelated secret env vars or requests for platform-wide credentials.
Persistence & Privilege
always is false. The skill asks to store a session_id for requests (normal per-session state) but does not request persistent system-wide privileges or modifications to other skills. Agent autonomous invocation remains allowed by default, which is normal for skills and not by itself a red flag.
Assessment
This skill is coherent with its stated purpose, but it will send your prompts, any uploaded images/files, and inferred install-path info to an external API (mega-api-prod.nemovideo.ai). Consider these points before installing:
- Privacy: do not upload sensitive images or files you don't want transmitted off your machine. The skill explicitly supports uploading local files.
- Token behavior: if you don't set NEMO_TOKEN, the skill will request an anonymous token from the service (100 free credits, 7 days) and use it for subsequent calls. If you prefer more control, obtain and set your own token from the provider (if available).
- Unknown source: the skill package has no homepage or clear publisher info. If you require vendor transparency or legal/privacy terms, seek the provider's policy for nemovideo.ai before using.
- Attribution header: the skill will detect install path to populate X-Skill-Platform — this requires reading an install path; if you are uncomfortable with any filesystem reads, do not install.
If you trust the remote service and do not intend to upload sensitive content, the permissions requested are proportionate to the skill's functionality. If you need higher assurance, request a verified publisher/homepage or run network activity through a controlled environment to observe what is sent.Like a lobster shell, security has layers — review code before you run it.
latestvk975d1jtszvwkr9j0407xekn75840dvb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🎬 Clawdis
EnvNEMO_TOKEN
Primary envNEMO_TOKEN
