Skills lipsync
📦

lipsync

Content revision r1 Medium Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Create Lip-Synced Videos with RunComfy

Lip-sync workflows require different models for existing videos, portraits, and scripts. This skill selects a suitable RunComfy route and prepares the corresponding CLI workflow.

Supports: Claude Codex Code(CC)
Maintain this Skill? Claim it 📊 69 Adequate

Install with my Agent

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

Agent request
Review the Skillstore skill "lipsync" from https://skillstore.io/skills/prime-skills-lipsync.md and its manifest at https://skillstore.io/api/skills/prime-skills-lipsync/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.

Markdown detail GET /skills/prime-skills-lipsync.md Signed manifest GET /api/skills/prime-skills-lipsync/manifest Signed lockfile GET /api/skills/prime-skills-lipsync/lockfile

Test it

Using "lipsync". I have an approved interview video and a translated voiceover. Final delivery quality matters more than cost.

Expected outcome:

  • Recommended route: Sync Labs sync v2 Pro.
  • Required inputs: source video URL and translated voiceover URL.
  • Preparation: use clean speech and align audio and video durations.
  • Next step: confirm rights and review the prepared invocation before submission.

Using "lipsync". I have my own portrait and a recording of my voice. I need a talking presenter.

Expected outcome:

  • Recommended route: OmniHuman.
  • Required inputs: portrait URL and voice recording URL.
  • Preparation: select a clear head-and-shoulders or upper-body portrait.
  • This route derives animation from the image and audio rather than a scene prompt.

Using "lipsync". I have an original script but no audio recording. I need speech and video together.

Expected outcome:

  • Consider Kling text-to-video lipsync or HappyHorse text-to-video.
  • These routes generate speech rather than matching a fixed recording.
  • Check the current model schema before preparing an invocation.

Security Audit

Medium Risk
v1 • 10/23/2026 Open versioned report

All 76 static findings are false positives involving Markdown, reference URLs, model-selection advice, or documented token storage. One semantic concern remains: the shell-injection safety claim overlooks unsafe shell interpolation of user-controlled JSON. No evidence found of malicious instructions or credential exfiltration; external CLI behavior was not independently verified.

1
Files scanned
237
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
SKILL.md:110-117SKILL.md:221
Shell Safety Claim Omits Host-Shell Quoting
The claim "No shell-injection surface" overlooks shell parsing before CLI execution. Directly inserting user-controlled JSON into the demonstrated single-quoted argument can permit command injection.
The examples use single-quoted JSON while the safety claim only addresses CLI expansion. Exploitation depends on unsafe interpolation; no executable vulnerable wrapper is supplied.

Risk Factors

⚙️ External commands (38)
SKILL.md:7 SKILL.md:24 SKILL.md:30-41 SKILL.md:41-43 SKILL.md:43-57 SKILL.md:57-62 SKILL.md:62-67 SKILL.md:67-72 SKILL.md:72-79 SKILL.md:79-80 SKILL.md:80-84 SKILL.md:84 SKILL.md:85-91 SKILL.md:91-96 SKILL.md:96 SKILL.md:97-105 SKILL.md:105 SKILL.md:110-117 SKILL.md:117-130 SKILL.md:130-135 SKILL.md:135-142 SKILL.md:142-148 SKILL.md:148-154 SKILL.md:154 SKILL.md:159-166 SKILL.md:166-187 SKILL.md:187 SKILL.md:194-214 SKILL.md:214 SKILL.md:219 SKILL.md:220 SKILL.md:221-226 SKILL.md:226 SKILL.md:228-232 SKILL.md:232-233 SKILL.md:233-234 SKILL.md:234-235 SKILL.md:235-236
🌐 Network access (28)
SKILL.md:18 SKILL.md:26 SKILL.md:43 SKILL.md:62 SKILL.md:67 SKILL.md:72 SKILL.md:91 SKILL.md:106 SKILL.md:113 SKILL.md:114 SKILL.md:124 SKILL.md:131 SKILL.md:138 SKILL.md:139 SKILL.md:148 SKILL.md:155 SKILL.md:162 SKILL.md:163 SKILL.md:187 SKILL.md:193 SKILL.md:194 SKILL.md:195 SKILL.md:210 SKILL.md:232 SKILL.md:233 SKILL.md:234 SKILL.md:235 SKILL.md:236
📁 Filesystem access (2)
SKILL.md:220 SKILL.md:220
Audited by: codex
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/prime-skills-lipsync/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/prime-skills-lipsync/security.svg)](https://skillstore.io/skills/prime-skills-lipsync?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/prime-skills-lipsync.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

prime-skills. (2026). lipsync security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prime-skills-lipsync/audits/1

BibTeX citation

@techreport{prime-skills-prime-skills-lipsync-2026, author = {prime-skills}, title = {lipsync security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/prime-skills-lipsync/audits/1}, 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: "lipsync security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "prime-skills" date-released: "2026-10-23" url: "https://skillstore.io/skills/prime-skills-lipsync/audits/1" identifiers: - type: other value: "skillstore:prime-skills-lipsync:audit:1" description: "Skillstore immutable audit report identifier"

Compare variants

4 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
prime-skills Recommended Current

prime-skills-lipsync

Skillstore Score 69
Evidence Confidence Medium
Skillstore usage 2
Updated

2026-10-24

agentspace-so

agentspace-so-lipsync

Skillstore Score 38
Evidence Confidence High
Skillstore usage 48
Updated

2026-10-22

runcomfy-com

runcomfy-com-lipsync

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 43
Updated

2026-09-09

doany-ai

doany-ai-lipsync

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 43
Updated

2026-09-09

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
65
Community
83
Spec Compliance

What You Can Build

Localize an Existing Video

Pair an authorized source video with translated voiceover and choose the appropriate Sync Labs tier.

Animate a Presenter Portrait

Use an approved portrait and voice recording to prepare an OmniHuman presenter workflow.

Choose a Script-Based Route

Compare documented generation routes for an original script when no recorded voiceover is available.

Try These Prompts

Choose a Lip-Sync Model 
I have an authorized video and voiceover recording. Recommend the simplest lip-sync route and list the required inputs without running anything.
Prepare a Talking Portrait 
Prepare an OmniHuman workflow using [portrait URL] and [audio URL]. Confirm face and voice consent, and show the invocation before execution.
Plan a Premium Video Dub 
Use [video URL] and [translated audio URL] for a consented premium dub. Check duration alignment and prepare Sync Labs Pro arguments.
Plan a Multilingual Production 
Plan separate OmniHuman jobs for [portrait URL] and [audio URL list]. Confirm consent, safely serialize inputs, and separate outputs. Request approval before execution.

Best Practices

  • Confirm permission for both the face and voice before sending assets to an external generation service.
  • Use clean voice recordings and align audio duration with the source video.
  • Pass serialized JSON as a literal argument through an argument-array API or apply shell-safe quoting.

Avoid

  • Using a real person's face or voice without permission.
  • Choosing script-generated speech when exact synchronization to an existing recording is required.
  • Inserting untrusted prompts or URLs directly into shell command text.

Frequently Asked Questions

Which model should I use for an existing video?
The skill recommends Sync Labs sync v2 for drafts and Pro for premium delivery. Kling and Creatify are alternative routes.
Can I start with a single portrait?
Yes. The documented OmniHuman route accepts a portrait URL and an audio URL.
Can I generate speech from a script?
The skill recommends Kling text-to-video lipsync or HappyHorse. Check current model documentation because complete script-route commands are not included.
Does the skill run locally?
The CLI runs locally, but generation uses RunComfy's hosted Model API. Authentication and network access are required.
Does the skill enforce consent automatically?
No. It instructs operators to confirm face and voice consent, but does not implement an input gate.
How are results saved?
The documented workflow downloads supported RunComfy result URLs into the output directory selected through the CLI.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/prime-skills/runcomfy-agent-skills/tree/fca19ae084c2ae4667f5c8affbb99da5103d5832/lipsync

Ref

5893493b99d0bdd120c437906b07718a60acc880

Maintenance freshness

10/23/2026

Usage

0 downloads · 0 views

File structure

📄 SKILL.md

More from prime-skills

View all

Related Skills

View all