ai-video-generation
Create AI Videos with inference.sh
AI video workflows require careful model and option choices. This skill helps Claude, Codex, and Claude Code run inference.sh video models for generation, avatars, lipsync, and utilities.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "ai-video-generation" from https://skillstore.io/skills/tool-belt-ai-video-generation.md and its manifest at https://skillstore.io/api/skills/tool-belt-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.
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". Create a five-second product teaser for a new desk lamp.
Expected outcome:
- Suggested a fast draft model for social review.
- Asked for aspect ratio, product style, and brand tone.
- Prepared a concise prompt and confirmation step before running the job.
Using "ai-video-generation". Animate a portrait with voice narration.
Expected outcome:
- Recommended an avatar or lipsync model based on the media type.
- Warned that face and voice consent is required.
- Requested approved media URLs before using the CLI.
Using "ai-video-generation". Improve a silent product clip.
Expected outcome:
- Chose upscaling or foley utilities based on the request.
- Planned separate enhancement steps to reduce cost and failed reruns.
Security Audit
Medium RiskMost static external-command alerts are false positives caused by Markdown code fences and inline code spans. The skill intentionally grants Bash(infsh *) and sends prompts or media URLs through inference.sh. No prompt injection or credential exfiltration language was found.
Confirmed security concerns (2)
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.
Risk Factors
⚙️ External commands (47)
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/tool-belt-ai-video-generation/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/tool-belt-ai-video-generation?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/tool-belt-ai-video-generation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/tool-belt-ai-video-generation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/tool-belt-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
tool-belt. (2026). ai-video-generation security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/tool-belt-ai-video-generation/audits/5BibTeX citation
@techreport{tool-belt-tool-belt-ai-video-generation-2026,
author = {tool-belt},
title = {ai-video-generation security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/tool-belt-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: "tool-belt"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/tool-belt-ai-video-generation/audits/5"
identifiers:
- type: other
value: "skillstore:tool-belt-ai-video-generation:audit:5"
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
runcomfy-com-ai-video-generation
2026-08-21
inferen-sh-ai-video-generation
2026-08-21
inference-shell-ai-video-generation
2026-08-21
agentspace-so-ai-video-generation
2026-08-21
doany-ai-ai-video-generation
2026-08-21
halt-catch-fire-ai-video-generation
2026-08-21
inference-sh-skills-ai-video-generation
2026-08-21
skills-collective-ai-video-generation
2026-08-21
skillssh-ai-video-generation
2026-08-21
tool-belt-ai-video-generation
2026-08-21
skills-shell-ai-video-generation
2026-08-21
inference-skills-ai-video-generation
2026-08-21
qu-skills-ai-video-generation
2026-08-21
tul-sh-ai-video-generation
2026-08-21
toolshell-ai-video-generation
2026-08-21
infsh-skills-ai-video-generation
2026-08-21
101-skills-ai-video-generation
2026-08-21
danielgwilson-ai-video-generation
2026-08-21
genmedia-labs-ai-video-generation
2026-08-21
inference-sh-ai-video-generation
2026-08-21
inference-sh-9-ai-video-generation
2026-08-21
inference-sh-8-ai-video-generation
2026-08-21
prime-skills-ai-video-generation
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Create Short Social Videos
Draft short clips for posts, reels, and ads while choosing fast models for iteration.
Plan Marketing Video Assets
Compare video models for product demos, explainers, campaign clips, and visual experiments.
Prototype Media Pipelines
Combine generation, upscaling, foley, lipsync, and merging steps for repeatable video workflows.
Try These Prompts
Help me create a simple AI video. Ask for the subject, style, duration, aspect ratio, and target platform. Recommend one model before running anything.
Turn this approved image URL into a short video: [URL]. Ask for motion, mood, duration, and platform. Confirm consent before using inference.sh.
Plan a complete video pipeline for [campaign]. Include model choices for image-to-video, sound effects, upscaling, and final merging. Ask before each paid run.
Compare three model options for [goal] by speed, quality, audio support, cost risk, and input requirements. Recommend a draft path and final path.
Best Practices
- Confirm rights and consent for faces, voices, audio, and source media before avatar or lipsync work.
- Use non-sensitive media URLs unless the account and provider policy allow confidential data.
- Start with fast models for drafts, then switch to higher-quality models for final renders.
Avoid
- Running video jobs with private customer images or voices without consent.
- Using placeholder URLs instead of accessible media files.
- Installing related skills or tools during a video task without explicit approval.