Skills ai-avatar-video
📦
ai-avatar-video
Content revision r1 Medium Risk ⚙️ External commands🌐 Network access
Create AI Avatar Videos With CLI Workflows
AI avatar video creation often requires choosing models, voices, audio, and CLI options. This skill provides ready workflows for talking heads, dubbing, and UGC-style presenters.
Supports: Claude Codex Code(CC)
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-avatar-video" from https://skillstore.io/skills/qu-skills-ai-avatar-video.md and its manifest at https://skillstore.io/api/skills/qu-skills-ai-avatar-video/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-avatar-video". Create a quick presenter video from a portrait and short script.
Expected outcome:
- Recommended P-Video-Avatar because it includes text-to-speech.
- Use a front-facing portrait with good lighting and a short approved script.
- Review the generated video for likeness, voice tone, disclosure, and brand accuracy.
Using "ai-avatar-video". Dub an existing product video into another language.
Expected outcome:
- Transcribe the source audio first, then translate the approved text.
- Generate clean speech in the target language before running lipsync.
- Check timing, pronunciation, consent, and final subtitles before publishing.
Using "ai-avatar-video". Produce several disclosed ad variants with different presenters.
Expected outcome:
- Create a small set of approved portrait and voice combinations.
- Keep claims consistent across variants and avoid fake personal endorsements.
- Track each output with campaign, presenter, voice, language, and approval status.
Security Audit
Medium Riskv4 • 7/5/2026 Open versioned report
Most static external-command alerts are Markdown fences or inline model names, but the skill does include real belt and npx command guidance. Hardcoded URL alerts are mostly documentation or placeholder media URLs; the main residual concerns are external media processing and synthetic avatar misuse without clear user safeguards. No prompt injection attempt was found in SKILL.md.
1
Files scanned
268
Lines analyzed
16
Review items
0
False positives ignored
Confirmed security concerns (2)
Medium
Third-Party Media Processing Disclosure Gap
The workflows submit portrait images, audio URLs, scripts, and transcripts to external inference apps through the belt CLI. The skill does not warn users to avoid confidential or unlicensed media before upload.
The cited commands include image, audio, text, and transcript inputs sent to inference apps. No nearby privacy or data-handling warning appears in the skill text.
Medium
Synthetic Testimonial and Likeness Misuse Risk
The skill promotes UGC-style avatar ads and talking presenters, including testimonial wording from a generated presenter. Without consent and disclosure guidance, this can support deceptive endorsements or impersonation.
The cited sections explicitly describe UGC marketing, virtual presenters, and avatar testimonial content. The same sections do not include consent, likeness-rights, or disclosure safeguards.
Capability review items (16)
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`
This line tells users to run npx to add an external CLI skill, which can execute or install remote code. That creates a supply-chain risk if copied without source verification.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The workflow runs belt commands and writes outputs to local JSON files while sending media or text inputs to remote inference apps. This is legitimate for the skill, but it is real external command and data processing behavior.
Medium
Ruby/shell backtick execution
```bash
The workflow runs belt commands and writes outputs to local JSON files while sending media or text inputs to remote inference apps. This is legitimate for the skill, but it is real external command and data processing behavior.
Medium
Ruby/shell backtick execution
```bash
The fenced example runs belt app commands against remote avatar or lipsync models. The commands are scoped and documented, but they execute an external CLI and submit user media or script inputs.
Medium
Ruby/shell backtick execution
```bash
The block contains a shell loop that runs belt app jobs against a remote inference service. The loop uses hardcoded values, but it is still real external command execution.
Medium
Ruby/shell backtick execution
```bash
This block recommends multiple npx skills add commands for external skills. Installing extra remote skills expands the trusted code and instruction surface.
Medium
Ruby/shell backtick execution
```
The range includes an inline belt app store command that would query a remote app catalog if executed. It has no dynamic input, so confidence is lower, but it remains external CLI use.
Low
Hardcoded URL
SKILL.md:7 SKILL.md:17 SKILL.md:19-28 SKILL.md:28-36 SKILL.md:36-37 SKILL.md:37-38 SKILL.md:38-39 SKILL.md:39-55 SKILL.md:55-63 SKILL.md:63-67 SKILL.md:67-76 SKILL.md:76-80 SKILL.md:80-85 SKILL.md:85-91 SKILL.md:91-104 SKILL.md:104-108 SKILL.md:108-113 SKILL.md:113-119 SKILL.md:119-124 SKILL.md:124-128 SKILL.md:128-133 SKILL.md:133-139 SKILL.md:139-152 SKILL.md:152-158 SKILL.md:158-172 SKILL.md:172-178 SKILL.md:178-194 SKILL.md:194-206 SKILL.md:206-218 SKILL.md:218-235 SKILL.md:235 SKILL.md:241-259 SKILL.md:259-261
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/qu-skills-ai-avatar-video/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/qu-skills-ai-avatar-video?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/qu-skills-ai-avatar-video?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/qu-skills-ai-avatar-video/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/qu-skills-ai-avatar-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
qu-skills. (2026). ai-avatar-video security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/qu-skills-ai-avatar-video/audits/4BibTeX citation
@techreport{qu-skills-qu-skills-ai-avatar-video-2026,
author = {qu-skills},
title = {ai-avatar-video security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/qu-skills-ai-avatar-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: "ai-avatar-video security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "qu-skills"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/qu-skills-ai-avatar-video/audits/4"
identifiers:
- type: other
value: "skillstore:qu-skills-ai-avatar-video:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
11 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-avatar-video
Skillstore Score 79
Evidence Confidence High
Skillstore usage 9
Updated
2026-08-21
inference-sh-skills-ai-avatar-video
Skillstore Score 79
Evidence Confidence High
Skillstore usage 5
Updated
2026-08-21
infsh-skills-ai-avatar-video
Skillstore Score 69
Evidence Confidence High
Skillstore usage 12
Updated
2026-08-21
inference-skills-ai-avatar-video
Skillstore Score 69
Evidence Confidence High
Skillstore usage 10
Updated
2026-08-21
skills-shell-ai-avatar-video
Skillstore Score 50
Evidence Confidence High
Skillstore usage 24
Updated
2026-08-21
halt-catch-fire-ai-avatar-video
Skillstore Score 50
Evidence Confidence High
Skillstore usage 13
Updated
2026-08-21
qu-skills Current
qu-skills-ai-avatar-video
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
agentspace-so-ai-avatar-video
Skillstore Score 38
Evidence Confidence High
Skillstore usage 7
Updated
2026-08-21
doany-ai-ai-avatar-video
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated
2026-08-21
inference-sh-ai-avatar-video
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
101-skills-ai-avatar-video
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 6
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
67
Community
91
Spec Compliance
What You Can Build
Create Disclosed Product Presenters
Plan avatar videos for product demos, onboarding clips, and short ads with clear synthetic presenter disclosure.
Produce Training Explainers
Turn approved scripts and presenter portraits into course introductions, policy explainers, or internal learning videos.
Localize Existing Videos
Plan transcription, translation, text-to-speech, and lipsync steps for multilingual video versions.
Try These Prompts
Create a Basic Avatar Video
Use this skill to plan a P-Video-Avatar run for a 30-second product welcome. Include portrait requirements, script notes, voice choice, and resolution.
Compare Avatar Models
Compare P-Video-Avatar, OmniHuman, Fabric, and PixVerse for my project. I need a talking presenter, clear lipsync, and a low budget.
Plan a Dubbing Workflow
Design a workflow to dub an existing two-minute video into Spanish. Include transcription, translation, speech generation, lipsync, and review checkpoints.
Design a Batch UGC Workflow
Plan a batch workflow for five disclosed UGC-style avatar ads. Include presenter variation, voice direction, file naming, privacy checks, and approval steps.
Best Practices
- Use only portraits, voices, scripts, and source videos you have permission to use.
- Disclose synthetic presenters clearly when videos are used for ads, education, or public communication.
- Review every command plan before running belt because media and scripts may leave the local environment.
Avoid
- Using a real person's likeness, voice, or video without documented permission.
- Uploading confidential scripts, unreleased assets, or private recordings to external generation jobs.
- Publishing avatar testimonials that imply real customer experience without clear disclosure.
Frequently Asked Questions
Does this skill generate videos by itself?
No. It guides an AI assistant to use the inference.sh belt CLI and supported avatar models.
What setup is required?
You need the belt CLI, an inference.sh account, and access to the models used in the workflow.
Which model should I try first?
Start with P-Video-Avatar for simple talking-head videos because it includes text-to-speech support.
Can I use real people in avatar videos?
Use real people only with permission, proper rights, and clear disclosure when the result is synthetic.
Where is my media processed?
The workflows send selected inputs to inference.sh apps or related model providers through the belt CLI.
Does this replace human review?
No. Review every output for accuracy, consent, disclosure, brand safety, and legal requirements before publishing.