📦
agent-tools
38Run AI Apps with inference.sh
Teams need one CLI workflow for many hosted AI models and media tools. This skill helps Claude, Codex, and Claude Code discover apps, run tasks, and track results.
DevOps & Infrastructure View
Skills ai-video-generation
📦
ai-video-generation
Content revision r1 Critical ⚙️ External commands🌐 Network access
Create AI Video Workflows
AI video tasks require matching prompts, models, and CLI options. This skill guides inference.sh video generation, animation, lipsync, upscaling, and media merging.
Supports: Claude Codex Code(CC)
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 "ai-video-generation" from https://skillstore.io/skills/inference-sh-8-ai-video-generation.md and its manifest at https://skillstore.io/api/skills/inference-sh-8-ai-video-generation/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.
Test it
Using "ai-video-generation". User asks for a five-second forest drone shot with audio.
Expected outcome:
The skill recommends Veo 3.1 Fast, drafts a concise prompt, and notes that the CLI will contact inference.sh.
Using "ai-video-generation". User has a portrait and narration audio for a training clip.
Expected outcome:
The skill compares avatar and lipsync models, then suggests approved asset URLs and privacy checks before generation.
Using "ai-video-generation". User wants to finish two generated clips.
Expected outcome:
The skill suggests foley, upscaling, and a fade transition workflow using the media utilities.
Security Audit
Criticalv4 • 7/6/2026 Open versioned report
Most external-command findings are Markdown backtick false positives or documented infsh examples. The quick start contains a real curl-to-sh installer pattern and hardcoded installer URL, which are unsafe for automatic trust. No prompt-injection text or additional semantic malware intent was found.
1
Files scanned
178
Lines analyzed
2
Review items
0
False positives ignored
Confirmed security concerns (1)
Critical
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh && infsh login
Line 17 instructs users or agents to execute network-delivered shell code with curl piped into sh. This pattern can run arbitrary installer code without local review.
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
High
Ruby/shell backtick execution
```bash
The quick start range contains a curl command piped directly to sh before login. A community skill recommending remote installer execution creates a supply-chain risk.
High
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh && infsh login
The hardcoded URL is used as the source for a remote installer that is piped into sh. This is a real network trust risk, not a passive documentation link.
Risk Factors
⚙️ External commands (43)
SKILL.md:15-21 SKILL.md:21-23 SKILL.md:23-31 SKILL.md:31-32 SKILL.md:32-33 SKILL.md:33-34 SKILL.md:34-35 SKILL.md:35-36 SKILL.md:36-37 SKILL.md:37-38 SKILL.md:38-44 SKILL.md:44-45 SKILL.md:45-46 SKILL.md:46-52 SKILL.md:52-53 SKILL.md:53-54 SKILL.md:54-55 SKILL.md:55-61 SKILL.md:61-62 SKILL.md:62-63 SKILL.md:63-67 SKILL.md:67-69 SKILL.md:69-75 SKILL.md:75-79 SKILL.md:79-83 SKILL.md:83-88 SKILL.md:88-92 SKILL.md:92-96 SKILL.md:96-100 SKILL.md:100-105 SKILL.md:105-109 SKILL.md:109-114 SKILL.md:114-118 SKILL.md:118-123 SKILL.md:123-127 SKILL.md:127-129 SKILL.md:129-133 SKILL.md:133-138 SKILL.md:138-142 SKILL.md:142-147 SKILL.md:147-151 SKILL.md:151-169 SKILL.md:169-171
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.
Copy report link
https://skillstore.io/skills/inference-sh-8-ai-video-generation/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/inference-sh-8-ai-video-generation?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/inference-sh-8-ai-video-generation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-8-ai-video-generation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/inference-sh-8-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
inference-sh-8. (2026). ai-video-generation security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-8-ai-video-generation/audits/4BibTeX citation
@techreport{inference-sh-8-inference-sh-8-ai-video-generation-2026,
author = {inference-sh-8},
title = {ai-video-generation security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-8-ai-video-generation/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: "ai-video-generation security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-sh-8"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/inference-sh-8-ai-video-generation/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-8-ai-video-generation:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
23 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Higher Skillstore usage
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
runcomfy-com Recommended
runcomfy-com-ai-video-generation
Skillstore Score 78
Evidence Confidence High
Skillstore usage 26
Updated
2026-09-09
inferen-sh-ai-video-generation
Skillstore Score 78
Evidence Confidence High
Skillstore usage 12
Updated
2026-09-09
inference-shell-ai-video-generation
Skillstore Score 78
Evidence Confidence High
Skillstore usage 12
Updated
2026-09-09
agentspace-so-ai-video-generation
Skillstore Score 78
Evidence Confidence High
Skillstore usage 11
Updated
2026-09-09
doany-ai-ai-video-generation
Skillstore Score 78
Evidence Confidence High
Skillstore usage 8
Updated
2026-09-09
halt-catch-fire-ai-video-generation
Skillstore Score 75
Evidence Confidence High
Skillstore usage 45
Updated
2026-09-09
inference-sh-skills-ai-video-generation
Skillstore Score 75
Evidence Confidence High
Skillstore usage 8
Updated
2026-09-09
skills-collective-ai-video-generation
Skillstore Score 74
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-09-09
tool-belt-ai-video-generation
Skillstore Score 69
Evidence Confidence High
Skillstore usage 10
Updated
2026-09-09
skills-shell-ai-video-generation
Skillstore Score 69
Evidence Confidence High
Skillstore usage 10
Updated
2026-09-09
inference-skills-ai-video-generation
Skillstore Score 69
Evidence Confidence High
Skillstore usage 6
Updated
2026-09-09
qu-skills-ai-video-generation
Skillstore Score 68
Evidence Confidence High
Skillstore usage 22
Updated
2026-09-09
tul-sh-ai-video-generation
Skillstore Score 50
Evidence Confidence High
Skillstore usage 20
Updated
2026-09-09
toolshell-ai-video-generation
Skillstore Score 50
Evidence Confidence High
Skillstore usage 19
Updated
2026-09-09
skillssh-ai-video-generation
Skillstore Score 50
Evidence Confidence High
Skillstore usage 13
Updated
2026-09-09
infsh-skills-ai-video-generation
Skillstore Score 50
Evidence Confidence High
Skillstore usage 13
Updated
2026-09-09
danielgwilson-ai-video-generation
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 6
Updated
2026-09-09
101-skills-ai-video-generation
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 6
Updated
2026-09-09
genmedia-labs-ai-video-generation
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 3
Updated
2026-09-09
inference-sh-ai-video-generation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 40
Updated
2026-09-09
inference-sh-9-ai-video-generation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 24
Updated
2026-09-09
inference-sh-8 Current
inference-sh-8-ai-video-generation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated
2026-09-09
prime-skills-ai-video-generation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 3
Updated
2026-09-09
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance
What You Can Build
Draft Marketing Clips
Create short concept clips, product teasers, and campaign visuals before commissioning final production.
Prototype Avatar Lessons
Plan talking-head lessons or narrated explainers from approved portraits and audio.
Finish Generated Media
Upscale clips, add foley effects, or merge generated scenes into a simple sequence.
Try These Prompts
Create a Simple Video
Use this skill to recommend a text-to-video model and prepare a safe command for a 5 second clip about [topic].
Animate an Image
Use this skill to choose an image-to-video model for [image URL] and define motion, camera style, duration, and quality settings.
Build an Avatar Clip
Use this skill to compare OmniHuman, Fabric, and PixVerse for a talking-head video using approved image and audio assets.
Plan a Full Pipeline
Use this skill to design a workflow that generates scenes, adds foley, upscales clips, and merges them into one final video.
Best Practices
- Review remote installer commands before running them.
- Use approved media URLs and avoid confidential images, voices, or unreleased footage.
- Choose the smallest model and duration that can validate the creative direction.
Avoid
- Do not pipe remote install scripts directly into a shell.
- Do not upload private portraits, voices, or customer media without consent.
- Do not assume placeholder URLs in examples are production-ready inputs.
Frequently Asked Questions
What does this skill help with?
It helps choose inference.sh video models and prepare CLI workflows for video generation and finishing.
Does it generate videos locally?
No. It uses the inference.sh CLI and remote model providers to create or process videos.
Which assistants can use it?
The report lists support for Claude, Codex, and Claude Code.
What must be installed first?
Users need the inference.sh CLI, account access, login, and network connectivity.
Can it use image and audio inputs?
Yes. Supported models accept approved image, audio, or video URLs for animation, avatars, lipsync, and finishing.
What is the main security concern?
The quick start uses a remote installer piped to a shell. Review and verify installer steps before running commands.
Developer Details
Author
inference-sh-8License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a06681402992ceae98ba04d54cfd4ab004862696
Maintenance freshness
7/18/2026
Usage
6 downloads · 169 views
File structure
📄 SKILL.md
More from inference-sh-8
View all📦
agent-browser
38Automate Browser Workflows with Agent Browser
Manual browser tasks slow down research, testing, and form workflows. This skill uses inference.sh sessions to navigate pages, interact with elements, capture evidence, and extract page content.
Productivity View
📦
ai-image-generation
38Generate AI Images with inference.sh
Creating model-specific image prompts and commands can slow visual work. This skill provides inference.sh examples for generation, editing, upscaling, and model selection.
Design & Creative View
📦
twitter-automation
38Automate Twitter/X Workflows
Manual Twitter/X posting and engagement can slow repeatable social workflows. This skill guides Claude, Codex, and Claude Code through inference.sh CLI actions for posts, media, DMs, follows, and lookups.
Communication View
📦
remotion-render
38Render Remotion Videos from React Code
Creating animated videos from React components is hard to package and render reliably. This skill sends Remotion TSX to inference.sh and returns an MP4 render.
Design & Creative View
Related Skills
View all📦
ai-avatar-video
79Create AI Avatar Videos
by inference-sh-skills
Teams need presenter videos, dubbing, and lip-sync clips without a full studio. This skill guides Claude, Codex, and Claude Code through inference.sh CLI workflows for avatar video generation.
Design & Creative View
📦
p-video
78Generate Pruna Videos from Text and Images
by inferen-sh
Creating video model commands requires choosing compatible inputs and settings. This skill guides Pruna P-Video and WAN generation through the inference.sh CLI.
Design & Creative View
📦
image-to-video
78Animate Images with RunComfy Video Models
by runcomfy-com
Still images need the right model and prompt to become useful video clips. This skill routes image-to-video requests to RunComfy models with matching settings and examples.
Design & Creative View
📦
seedance
80Create Seedance Video Prompts
by songguoxs
Video creators need structured Chinese prompts for Seedance workflows. This skill builds prompt plans for scenes, references, timing, sound, and extensions.
Design & Creative View
📦
controlnet-pose
79Create Pose-Controlled Images and Videos
by runcomfy-com
Pose-controlled generation often requires choosing the right model and input format. This skill routes image and video requests to RunComfy workflows.
Design & Creative View
📦
qwen-image-2-pro
79Generate Text-Rich Images with Qwen Pro
by inference-shell
Design teams need image prompts that preserve text and layout details. This skill guides Claude, Codex, or Claude Code to call Qwen-Image-2-Pro through inference.sh.
Design & Creative View