Veo 3 Video Gen (Gemini API)
v0.1.0Generate and stitch short videos via Google Veo 3.x using the Gemini API (google-genai). Use when you need to create video clips from prompts (ads, UGC-style clips, product demos) and want a reproducible CLI workflow (generate, poll, download MP4, optionally stitch multiple segments).
⭐ 2· 2.9k·9 current·9 all-time
by@bluelyw
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The code and SKILL.md align with the stated purpose (generate and stitch Veo/Gemini video segments). However the registry metadata claims no required env vars/binaries while the instructions and script require GEMINI_API_KEY and (when using multiple segments) ffmpeg. The script also lists python dependencies (google-genai, pillow) in header comments but there is no install spec — this mismatch is disproportionate to the stated metadata.
Instruction Scope
The runtime instructions and the script stay within the stated scope: call the Gemini API via the google-genai SDK, poll for results, download/save video files, optionally extract frames and concatenate via ffmpeg. The SKILL.md and script do not attempt to read unrelated system files or external endpoints beyond the Gemini API and local reference-image paths. Note: the script prints MEDIA: lines for each segment (explicitly documented) which some agent hosts may auto-attach/upload — that behavior should be expected and reviewed.
Install Mechanism
There is no install spec (instruction-only), which minimizes automatic disk writes, but the script includes dependency declarations (google-genai, pillow) and requires Python >=3.10. Because dependencies are not installed automatically, users must install them themselves. This is consistent with an instruction-only skill but is an operational gap (the metadata should mention these requirements).
Credentials
The registry metadata lists no required env vars, but SKILL.md and the script require GEMINI_API_KEY (or --api-key) to call Gemini. That credential is proportionate to the purpose, but its omission from the declared requirements is an incoherence. The script does not request unrelated secrets or other service credentials.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide configs, and only writes its own output files. It uses subprocess to run ffmpeg and shell checks, which is expected for media processing. No elevated/system-wide privileges are requested.
What to consider before installing
This skill appears to implement Veo/Gemini video generation as advertised, but the package metadata is inconsistent and the source is 'unknown.' Before installing or running it: (1) Treat GEMINI_API_KEY as required — only provide an API key you trust and that has appropriate billing/quota limits. (2) Be prepared to install python deps (google-genai, pillow) and ensure ffmpeg is on PATH if you plan to concatenate segments. (3) Review the script contents locally (it is included) — there are no hidden remote endpoints, but it uses subprocess/ffmpeg and prints MEDIA: lines which some hosts may auto-attach/upload outputs. (4) Run in an isolated environment or test account if you are unsure about billing or data exfiltration. (5) Ask the publisher (or avoid) if you need the package metadata corrected — the omission of required env vars/install instructions is a red flag for sloppy or incomplete packaging.Like a lobster shell, security has layers — review code before you run it.
latestvk971ec5n1rhbc8f3e951a5bg6d803a04
License
MIT-0
Free to use, modify, and redistribute. No attribution required.