Skills ai-video-generation
📦

ai-video-generation

Content revision r2 Medium Risk ⚙️ External commands🌐 Network access

Create AI Videos with Inference Models

Choosing and invoking video models can require extensive platform knowledge. This skill provides model guidance and adaptable belt CLI workflows.

Supports: Claude Codex Code(CC)
⚠️ 50 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "ai-video-generation" from https://skillstore.io/skills/infsh-skills-ai-video-generation.md and its manifest at https://skillstore.io/api/skills/infsh-skills-ai-video-generation/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Test it

Using "ai-video-generation". Create a five-second beach video quickly with synchronized ambient audio.

Expected outcome:

Recommended Seedance 2.0 Fast for rapid generation with synchronized audio. The workflow specifies a five-second sunset scene and wave sounds.

Using "ai-video-generation". Animate an authorized product photograph with gentle camera motion.

Expected outcome:

Recommended Wan 2.5 for image animation. The workflow preserves product shape, adds a slow orbit, and avoids changing labels.

Using "ai-video-generation". Create a talking presenter and improve the final video quality.

Expected outcome:

Use OmniHuman with authorized portrait and narration assets, then process the result through the Topaz upscaler after user approval.

Security Audit

Medium Risk
v5 • 8/6/2026 Open versioned report

The skill contains genuine external command and network behavior through documented belt and npx workflows. Most static backtick matches are Markdown fences or model identifiers, but command examples, third-party installation, remote image loading, and external media processing remain relevant risks.

1
Files scanned
253
Lines analyzed
20
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
External Processing of Sensitive Media
The examples submit portrait, audio, and video references to hosted inference services. Users may expose personal, biometric, copyrighted, or confidential media.
The cited belt examples explicitly pass remote portrait, audio, and video URLs to hosted model applications.
Capability review items (20)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
Line 7 instructs the user or agent to execute npx against a third-party skill source. This creates supply-chain and package-execution risk.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt login and a networked model invocation. These commands cause authentication and external service side effects.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app list against the external platform. This is intentional external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes a hosted Veo model through belt. It causes external command, network, and potential billing side effects.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes a hosted Grok video model through belt. It causes external command, network, and potential billing side effects.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes Wan through belt with a remote image input. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example sends portrait and audio references to OmniHuman through belt. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example sends face and audio references to Fabric through belt. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes Seedance through belt and requests generated audio. It causes external service and potential billing side effects.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes Seedance through belt with an external image reference. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes Seedance through belt with a portrait reference. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes HappyHorse through belt. It causes external command, network, and potential billing side effects.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes video editing through belt with a remote video. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example sends portrait and audio references to PixVerse through belt. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes a hosted video upscaler through belt. It causes external command, network, and potential billing side effects.
Medium
Ruby/shell backtick execution
```bash
The fenced example sends a video to a hosted foley model through belt. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The fenced example sends two videos to the hosted media merger through belt. It performs external command and network activity.
Medium
Ruby/shell backtick execution
```bash
This fenced block contains nine npx installation commands for external skills. Executing them introduces third-party package and supply-chain risk.
Medium
Ruby/shell backtick execution
```
The detected span includes the direct instruction to run belt app list. This invokes the external CLI and platform.
Low
Hardcoded URL
![AI Video Generation](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kg2c0egyg
The Markdown image embeds a remote inference.sh cloud asset. Rendering it causes a request to an external host and can disclose request metadata.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/infsh-skills-ai-video-generation/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/infsh-skills-ai-video-generation/security.svg)](https://skillstore.io/skills/infsh-skills-ai-video-generation?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/infsh-skills-ai-video-generation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/infsh-skills-ai-video-generation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/infsh-skills-ai-video-generation.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

infsh-skills. (2026). ai-video-generation security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/infsh-skills-ai-video-generation/audits/5

BibTeX citation

@techreport{infsh-skills-infsh-skills-ai-video-generation-2026, author = {infsh-skills}, title = {ai-video-generation security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/infsh-skills-ai-video-generation/audits/5}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "ai-video-generation security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "infsh-skills" date-released: "2026-08-06" url: "https://skillstore.io/skills/infsh-skills-ai-video-generation/audits/5" identifiers: - type: other value: "skillstore:infsh-skills-ai-video-generation:audit:5" description: "Skillstore immutable audit report identifier"

Compare variants

23 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage
runcomfy-com Recommended

runcomfy-com-ai-video-generation

Skillstore Score 78
Evidence Confidence High
Skillstore usage 24
Updated

2026-08-21

inferen-sh-ai-video-generation

Skillstore Score 78
Evidence Confidence High
Skillstore usage 12
Updated

2026-08-21

inference-shell-ai-video-generation

Skillstore Score 78
Evidence Confidence High
Skillstore usage 12
Updated

2026-08-21

agentspace-so-ai-video-generation

Skillstore Score 78
Evidence Confidence High
Skillstore usage 9
Updated

2026-08-21

doany-ai-ai-video-generation

Skillstore Score 78
Evidence Confidence High
Skillstore usage 8
Updated

2026-08-21

halt-catch-fire-ai-video-generation

Skillstore Score 75
Evidence Confidence High
Skillstore usage 45
Updated

2026-08-21

inference-sh-skills-ai-video-generation

Skillstore Score 75
Evidence Confidence High
Skillstore usage 8
Updated

2026-08-21

skills-collective-ai-video-generation

Skillstore Score 74
Evidence Confidence Medium
Skillstore usage 5
Updated

2026-08-21

skillssh-ai-video-generation

Skillstore Score 70
Evidence Confidence High
Skillstore usage 13
Updated

2026-08-21

tool-belt-ai-video-generation

Skillstore Score 69
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

skills-shell-ai-video-generation

Skillstore Score 69
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

inference-skills-ai-video-generation

Skillstore Score 69
Evidence Confidence High
Skillstore usage 6
Updated

2026-08-21

qu-skills-ai-video-generation

Skillstore Score 68
Evidence Confidence High
Skillstore usage 21
Updated

2026-08-21

tul-sh-ai-video-generation

Skillstore Score 50
Evidence Confidence High
Skillstore usage 19
Updated

2026-08-21

toolshell-ai-video-generation

Skillstore Score 50
Evidence Confidence High
Skillstore usage 18
Updated

2026-08-21

infsh-skills Current

infsh-skills-ai-video-generation

Skillstore Score 50
Evidence Confidence High
Skillstore usage 11
Updated

2026-08-21

101-skills-ai-video-generation

Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 6
Updated

2026-08-21

danielgwilson-ai-video-generation

Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 5
Updated

2026-08-21

genmedia-labs-ai-video-generation

Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 2
Updated

2026-08-21

inference-sh-ai-video-generation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 35
Updated

2026-08-21

inference-sh-9-ai-video-generation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 23
Updated

2026-08-21

inference-sh-8-ai-video-generation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated

2026-08-21

prime-skills-ai-video-generation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 2
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
91
Spec Compliance

What You Can Build

Produce Campaign Clips

Select a model and prepare short promotional video generation inputs for social channels.

Animate Product Images

Turn an existing product image into a controlled motion sequence with optional audio.

Build Talking Avatars

Combine authorized portrait and narration assets for lipsynced presenter videos.

Try These Prompts

Choose a Video Model
Recommend one model for a [duration] video showing [subject and action]. Prioritize [speed, quality, cost, or audio]. Explain the choice.
Create a Text-to-Video Workflow
Prepare a belt workflow for a [duration] [resolution] video. Scene: [description]. Include camera movement, lighting, style, and audio requirements.
Animate a Reference Image
Use [authorized image URL] to create a video with [motion]. Preserve [identity or product details]. Add [audio requirement] and recommend settings.
Design a Multi-Step Video Pipeline
Plan a pipeline that generates [scenes], adds [foley or narration], upscales output, and merges clips. State model choices, dependencies, privacy checks, and approval points.

Best Practices

  • Confirm the selected provider, estimated cost, and command before running any generation.
  • Use only media with documented consent and rights, especially portraits and voice recordings.
  • Start with short, low-resolution tests before requesting longer or higher-resolution outputs.

Avoid

  • Do not submit confidential media through public URLs or unknown hosting services.
  • Do not install unpinned skills or packages without reviewing their source and version.
  • Do not generate realistic people or voices without consent, attribution, and policy review.

Frequently Asked Questions

Which tools can use this skill?
The report declares compatibility with Claude, Codex, and Claude Code.
Does this skill generate videos locally?
No. It prepares belt commands that invoke hosted inference.sh applications.
What setup is required?
Install the reviewed belt CLI, create an account, authenticate, and ensure network access.
Can it animate an existing image?
Yes. Several documented models accept an image or reference URL for animation.
Can it add audio or lipsync?
Yes. Documented workflows include generated audio, foley, talking avatars, and lipsync models.
How should sensitive media be handled?
Use authorized assets, avoid confidential content, review provider terms, and obtain consent before external processing.

Developer Details

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Ref

4121de961d1b6f2ffca856260e239505c302452c

Maintenance freshness

8/7/2026

Usage

9 downloads · 110 views

File structure

📄 SKILL.md