WeryAI video tool — anime replace

Replace or move an element in an existing HTTPS video with WeryAI anime-style processing (video-anime-replace). Use when the user wants anime-style object re...

Security Scan

The skill's requests, instructions, and included script are coherent with its stated purpose (running a WeryAI anime-replace workflow on a public HTTPS video) and there are no disproportionate environment, install, or persistence demands.

Purpose & Capability

Name/description match the required items: the skill needs Node and a single WERYAI_API_KEY to call WeryAI's video-anime-replace endpoint. There are no unrelated credentials or binaries requested.

Instruction Scope

SKILL.md and the CLI script consistently restrict inputs to public https:// video and image URLs, instruct the user not to pass local file paths, and require explicit user confirmation before paid submit/wait. The runtime instructions stay within the declared workflow.

Install Mechanism

There is no install spec (instruction-only for the platform). The only runtime dependency is Node (declared). The shipped runnable script is included in the repo; there are no downloads or archive extraction steps.

Credentials

Only WERYAI_API_KEY is required and used by the script. The SKILL.md and script both state they read only that env var and avoid other environment/config access. This is proportionate to the stated purpose.

Persistence & Privilege

always is false and the skill doesn't request persistent or elevated platform privileges. It does network calls to the declared WeryAI API (expected for this use).

Assessment

This skill appears to be what it says: a small Node CLI that calls WeryAI's video-anime-replace API using a single API key and public HTTPS URLs. Before installing/using: (1) verify the WERYAI_API_KEY you provide is scoped and billed appropriately (runs are paid); (2) confirm the video_url and image_url are public HTTPS links and that you want those assets sent to the third-party API; (3) inspect the included scripts locally (scripts/video_anime_replace.js) to be sure you are comfortable running them; (4) avoid using your broad or production API keys — use a key with limited scope or test account if possible; (5) ensure there are no extra sibling scripts in your copy (SKILL.md warns about other out-of-scope files) before running. Nothing in the package indicates hidden endpoints, unrelated credential access, or filesystem exfiltration.

This skill is self-contained: it documents and runs only the anime-replace workflow on an existing video given by URL. It is not text-to-video or image-to-video generation from scratch.

Entry script: scripts/video_anime_replace.js (alongside this SKILL.md).

Runtime: WERYAI_API_KEY, Node.js 18+.

Inputs: video_url and image_url must be public https:// URLs. This script does not read local files and does not perform upload-file flows.

What this package ships (verify before trust)

Canonical layout for this skill only:

• SKILL.md, eval.yaml
• scripts/video_anime_replace.js (the only runnable script in scope)

If your copy also contains scripts/video_gen.js, scripts/video_toolkits.js, references/WERYAI_VIDEO_API.md, or other CLIs, those files are not part of this skill’s contract — they may come from another repo sync or an over-broad install. Do not run them when you only want anime-replace; remove them or reinstall from a clean source. Inspect what you run: node scripts/video_anime_replace.js spec.

Other tools (multi-endpoint CLIs, local-file upload to growth/upload-file APIs, extra environment variables in those CLIs) are out of scope for this package. This skill’s script uses only WERYAI_API_KEY and public https:// URLs.

API surface (this tool only)

• Required: video_url, image_url (public https:// URLs)
• Optional: type (move | replace), resolution (480p | 580p | 720p)
• Defaults: type=replace, resolution=720p

From this skill root, run node scripts/video_anime_replace.js spec to print the full tool schema (endpoint, required fields, defaults, enums) as JSON.

Pre-submit gate (mandatory)

Do not run submit / wait until the user explicitly confirms URLs and non-default type / resolution. Paid runs are not idempotent.

Workflow

Prefer --dry-run to validate JSON. Use wait to submit and poll until the task finishes; use submit only when the user wants a task_id without blocking, then status for later checks. Share final URLs as Markdown links [Video](https://…).

CLI

From this skill root:

node scripts/video_anime_replace.js wait \
  --json '{"video_url":"https://example.com/video.mp4","image_url":"https://example.com/ref.jpg"}'

node scripts/video_anime_replace.js submit \
  --json '{"video_url":"https://example.com/video.mp4","image_url":"https://example.com/ref.jpg","type":"replace","resolution":"720p"}'

node scripts/video_anime_replace.js status --task-id <task-id>

Dry-run:

node scripts/video_anime_replace.js wait \
  --json '{"video_url":"https://example.com/video.mp4","image_url":"https://example.com/ref.jpg"}' \
  --dry-run

Security

Never write WERYAI_API_KEY into files. Keep only WERYAI_API_KEY set for this workflow; do not rely on undocumented env vars in sibling scripts if any were mistakenly present. The in-scope script reads only WERYAI_API_KEY (no other env keys). video_anime_replace.js accepts only https:// media URLs (no disk read / no upload-file). Base URL and poll intervals are constants in the script, not env-driven.

Do not pass local filesystem paths or run tools that accept them unless you have explicitly reviewed and consented to their upload behavior — that is never required for this skill.

Out of scope

• Any other WeryAI video-tool endpoints (subtitle, upscale, extend, face change, etc.)
• Text-to-video or image-to-video from scratch

References

• WeryAI llms.txt
• Submit Video Anime Replace Task