Skills image-to-video

📦

image-to-video

Name: image-to-video
Author: inference-sh-9

Content revision r1 Critical ⚙️ External commands🌐 Network access

Animate Still Images Into Video

Static images often need motion for social, product, or presentation use. This skill guides model choice, motion prompts, and workflow steps for image-to-video generation.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Do not auto-install this skill.

The canonical policy requires operator review before any installation action.

Install with my Agent

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

Agent request

Review the Skillstore skill "image-to-video" from https://skillstore.io/skills/inference-sh-9-image-to-video.md and its manifest at https://skillstore.io/api/skills/inference-sh-9-image-to-video/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

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

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/inference-sh-9-image-to-video.md Signed manifest GET /api/skills/inference-sh-9-image-to-video/manifest Signed lockfile GET /api/skills/inference-sh-9-image-to-video/lockfile

Test it

Using "image-to-video". A fashion product image with flowing fabric.

Expected outcome:

Recommended model: Fabric 1.0. Motion should emphasize gentle cloth ripples, restrained camera movement, and short clip length.

Using "image-to-video". A portrait that needs a subtle animated social clip.

Expected outcome:

Use Wan 2.5 i2v for face fidelity.
Prompt for breathing, blinking, soft hair movement, and stable camera framing.
Keep the clip near four seconds.

Using "image-to-video". A landscape image that should become a looping background.

Expected outcome:

Use subtle water, cloud, and light movement. Keep camera motion slow and limit duration for a cleaner loop.

Security Audit

Critical

v4 • 7/5/2026 Open versioned report

The critical confirmed issue is the quick-start command that pipes https://cli.inference.sh directly into sh. Most medium backtick findings are Markdown formatting, model identifiers, or visible infsh examples without hidden execution. The related npx install examples add supply-chain risk, so safer installation guidance is needed before publication.

Files scanned

239

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Critical

SKILL.md:14

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh && infsh login

The command curls a remote script and pipes it directly to sh before review. This is a classic remote code execution installation pattern.

Capability review items (4)

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

Critical

SKILL.md:14

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh && infsh login

The hardcoded URL is fetched by curl and piped directly into sh. A compromised server, DNS path, or script would execute code on the user machine.

High

SKILL.md:13-28

Ruby/shell backtick execution

```bash

The fenced shell block includes a remote install command piped into sh and executable CLI calls. Although it is Markdown, the skill presents it as a quick-start command for users or agents to run.

Medium

SKILL.md:231-236

Ruby/shell backtick execution

```bash

The related-skills block recommends npx commands that can fetch and install external packages or skills. This creates supply-chain risk if users run it without review.

Low

SKILL.md:30

Hardcoded URL

> **Install note:** The [install script](https://cli.inference.sh) only detects your OS/architecture

The install note documents remote installer and checksum URLs that users must trust. This is an explicit network dependency, though the text also mentions checksum verification.

Risk Factors

Detected Patterns

Pipe to shell pattern

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

Copy report link

https://skillstore.io/skills/inference-sh-9-image-to-video/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inference-sh-9-image-to-video/security.svg)](https://skillstore.io/skills/inference-sh-9-image-to-video?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inference-sh-9-image-to-video?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-9-image-to-video/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inference-sh-9-image-to-video.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

inference-sh-9. (2026). image-to-video security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-9-image-to-video/audits/4

BibTeX citation

@techreport{inference-sh-9-inference-sh-9-image-to-video-2026,
  author = {inference-sh-9},
  title = {image-to-video security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/inference-sh-9-image-to-video/audits/4},
  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: "image-to-video security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "inference-sh-9"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-sh-9-image-to-video/audits/4"
identifiers:
  - type: other
    value: "skillstore:inference-sh-9-image-to-video:audit:4"
    description: "Skillstore immutable audit report identifier"

Compare variants

8 installable variants

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

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

runcomfy-com Recommended

runcomfy-com-image-to-video

Skillstore Score 78

Evidence Confidence High

Skillstore usage 30

Updated

2026-08-21

genmedia-labs

genmedia-labs-image-to-video

Skillstore Score 74

Evidence Confidence Medium

Skillstore usage 2

Updated

2026-08-21

halt-catch-fire

halt-catch-fire-image-to-video

Skillstore Score 50

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

101-skills

101-skills-image-to-video

Skillstore Score 50

Evidence Confidence Medium

Skillstore usage 4

Updated

2026-08-21

skills-collective

skills-collective-image-to-video

Skillstore Score 50

Evidence Confidence Medium

Skillstore usage 1

Updated

2026-08-21

doany-ai

doany-ai-image-to-video

Skillstore Score 38

Evidence Confidence High

Skillstore usage 15

Updated

2026-08-21

agentspace-so

agentspace-so-image-to-video

Skillstore Score 38

Evidence Confidence High

Skillstore usage 5

Updated

2026-08-21

inference-sh-9 Current

inference-sh-9-image-to-video

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 13

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Social Video Clips

Turn campaign stills into short clips with subtle motion and clear camera direction.

Product Motion Tests

Choose a model and prompt style for product, fabric, or reflective object animation.

Creative Video Prototypes

Plan image generation, animation, upscaling, audio, and merge steps for a polished short video.

Try These Prompts

Beginner Landscape Animation

Help me animate this landscape image. Recommend a model and write a short prompt with subtle water, cloud, and light motion.

Choose The Right Model

Compare the available image-to-video models for my image type: [describe image]. Choose one model and explain the motion style.

Product Motion Prompt

Create an image-to-video prompt for a product shot. Include one camera move, subtle reflections, and a smooth premium pace.

Full Production Workflow

Design a complete still-to-video workflow for [goal]. Include source image preparation, animation, upscaling, audio, stitching, and quality checks.

Best Practices

Request subtle motion before dramatic action.
Choose the model based on subject type and desired motion style.
Keep clips short, then stitch multiple clips when longer duration is needed.

Avoid

Do not combine multiple conflicting camera directions in one prompt.
Do not ask for complex action scenes from a single still image.
Do not start from low-resolution source images when quality matters.

Frequently Asked Questions

What does this skill help create?

It helps turn still images into short videos using model selection and motion prompting guidance.

Does the skill generate video by itself?

No. It guides use of inference.sh models and CLI workflows for video generation.

Which model is best for realistic motion?

The guide recommends Wan 2.5 i2v for realistic motion and face fidelity.

Which model should I use for fabric or liquid motion?

The guide recommends Fabric 1.0 for cloth, fabric, liquid, and flowing material scenes.

How long should image-to-video clips be?

The guide recommends short clips, often two to five seconds, for higher quality results.

Are there security concerns?

Yes. The current quick start pipes a remote installer into sh and should be replaced with verified manual steps.

Developer Details

Author

inference-sh-9

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/inference-sh-9/skills/tree/main/skills/image-to-video/

Ref

a25199bc7d6b82598536822d1738eb5d5f54025b

Maintenance freshness

7/20/2026

Usage

11 downloads · 177 views

File structure

📄 SKILL.md