Kaiber Ai

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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.

What this means

A user may believe they are using Kaiber while their files, prompts, and render jobs are handled by a different cloud service.

Why it was flagged

The skill presents itself as Kaiber AI while authenticating to and sending work to NemoVideo endpoints, without explaining the relationship between the brand and the backend.

Skill content
displayName: 'Kaiber AI — Generate AI Animated Videos' ... primaryEnv: 'NEMO_TOKEN' ... API base: `https://mega-api-prod.nemovideo.ai`
Recommendation

Clearly disclose the actual provider and affiliation, and ask users to confirm they trust the NemoVideo endpoint before uploading media.

What this means

Private images, videos, audio, and prompts may leave the local environment and be processed by the provider.

Why it was flagged

The skill sends user-selected media and prompts to an external cloud API for rendering.

Skill content
**Upload**: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart files=@/path ... **API base**: `https://mega-api-prod.nemovideo.ai`
Recommendation

Do not upload sensitive or confidential media unless you trust the provider and understand its retention and privacy terms.

What this means

The skill can authenticate to the provider and use the associated credits or session; leaked tokens could allow unwanted use of that service context.

Why it was flagged

The skill uses or automatically provisions a provider token for authenticated API calls.

Skill content
Look for `NEMO_TOKEN` in the environment... Otherwise: Generate a UUID... POST ... `/api/auth/anonymous-token` ... Extract `data.token`
Recommendation

Use a dedicated token, avoid sharing it, and revoke or unset it when you no longer want the skill to access the service.

What this means

The provider's responses may cause the agent to perform edits or exports without showing every low-level step to the user.

Why it was flagged

The remote backend's GUI-style responses can drive follow-up API actions inside the session.

Skill content
Backend says ... 'click [button]' ... You do: Execute via API ... 'Export button' ... Execute export workflow
Recommendation

Keep actions limited to the active media project and confirm user-visible results before final export or download.

What this means

Users have less provenance information for deciding whether this is an official or trustworthy integration.

Why it was flagged

There is no local package to install, but the registry information does not establish an official source or homepage for the claimed service integration.

Skill content
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Recommendation

Verify the publisher and service relationship before providing tokens or uploading private media.