Skills lipsync

📦

lipsync

Name: lipsync
Author: runcomfy-com

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

Create Lip-Synced Videos with RunComfy

Lip-sync workflows often require choosing the right hosted model and command format. This skill routes face, video, audio, and script inputs to RunComfy lip-sync endpoints.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

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/runcomfy-com-lipsync.md and its manifest at https://skillstore.io/api/skills/runcomfy-com-lipsync/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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/runcomfy-com-lipsync.md Signed manifest GET /api/skills/runcomfy-com-lipsync/manifest Signed lockfile GET /api/skills/runcomfy-com-lipsync/lockfile

Test it

Using "lipsync". A product demo video and a Spanish voiceover need synced mouth movement.

Expected outcome:

The assistant recommends Sync Labs sync v2 Pro, checks duration alignment, and prepares a RunComfy run using the video and audio URLs.

Using "lipsync". A consented portrait photo and a short founder voiceover should become a presenter clip.

Expected outcome:

The assistant selects OmniHuman, explains portrait framing needs, and prepares the avatar-style lip-sync workflow.

Using "lipsync". A team has only a launch script and wants a generated speaker video.

Expected outcome:

The assistant recommends a text-to-video lip-sync route and explains that the audio will be generated rather than matched to a fixed recording.

Security Audit

High Risk

v4 • 7/5/2026 Open versioned report

Most static detections are Markdown backticks, documentation links, placeholder media URLs, or model-selection prose rather than executable code. The real risks are the disclosed external RunComfy processing boundary and the dual-use ability to create synthetic speech videos from faces and voices.

Files scanned

237

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (2)

High

SKILL.md:45-48 SKILL.md:216-225

Synthetic Media Consent and Impersonation Risk

The skill is designed to pair a face with separate audio and states that it does not gate inputs. This can enable non-consensual or defamatory synthetic speech if operators ignore consent checks.

The consent section explicitly describes lip-sync as dual-use and says the skill itself does not gate inputs. The later privacy section repeats the need to confirm face and voice consent.

Medium

SKILL.md:212-214 SKILL.md:226

External Processing of Face and Voice Media

The skill sends media URLs and generation requests to RunComfy hosted model APIs. This creates a privacy boundary for face, voice, and video assets even though the endpoint allowlist is disclosed.

The file says the CLI posts to the Model API, polls status, and downloads RunComfy URLs. It also lists the allowed outbound RunComfy domains.

Risk Factors

⚙️ External commands (38)

🌐 Network access (28)

📁 Filesystem access (2)

SKILL.md:220 SKILL.md:220

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/runcomfy-com-lipsync/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/runcomfy-com-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

runcomfy-com. (2026). lipsync security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/runcomfy-com-lipsync/audits/4

BibTeX citation

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

Compare variants

3 installable variants

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

Why this variant is first

Stronger evidence confidence

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

agentspace-so Recommended

agentspace-so-lipsync

Skillstore Score 38

Evidence Confidence High

Skillstore usage 10

Updated

2026-08-21

runcomfy-com Current

runcomfy-com-lipsync

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

doany-ai

doany-ai-lipsync

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Localize a Brand Video

Sync a translated voiceover to an approved product video while preserving the original framing and motion.

Create a Talking Avatar

Generate a presenter-style clip from a consented portrait and a recorded voiceover for social or product content.

Plan Multilingual Dubs

Choose the correct RunComfy route for repeated language versions using the same approved face or source video.

Try These Prompts

Sync an Existing Video

Lip-sync this approved source video to this voiceover audio. Use the best RunComfy route for high mouth fidelity and explain the required inputs.

Create a Talking Portrait

Turn this consented portrait into a speaking avatar using this audio file. Pick the best RunComfy model and note any framing or audio checks.

Generate from a Script

Create a short lip-synced video from this script. Choose a route that can generate speech in the same pass and explain the tradeoffs.

Design a Multi-Language Workflow

Plan a RunComfy lip-sync workflow for five approved language voiceovers, one source video, consent checks, duration matching, and output review.

Best Practices

Confirm consent for both the face and the voice before creating any synthetic speech video.
Use clean voice audio and match audio duration to the source video length before running the model.
Review generated output for identity drift, incorrect speech timing, and unintended visual changes.

Avoid

Do not lip-sync public figures, private people, or performers without explicit permission.
Do not use sensitive or confidential media URLs unless external hosted processing is approved.
Do not choose text-to-video routes when the mouth must match a specific pre-recorded voice.

Frequently Asked Questions

Does this skill run lip-sync models locally?

No. It uses the RunComfy CLI to send requests to hosted RunComfy model endpoints.

Which route is best for an existing video and audio file?

The skill recommends Sync Labs sync v2 Pro for premium mouth fidelity and Sync Labs sync v2 for scaled jobs.

Which route is best for a still portrait?

The skill recommends OmniHuman when a portrait and separate audio should become a talking avatar video.

Can it create speech from a script?

Yes. It can route script-only requests to models that generate speech during video creation.

Does the skill verify consent automatically?

No. Operators must verify consent for the target face, the speaker voice, and the intended use.

What inputs affect output quality most?

Clean speech audio, stable face visibility, matching duration, and the chosen model tier have the largest impact.

Developer Details

Author

runcomfy-com

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/runcomfy-com/skills/tree/main/lipsync/

Ref

62e2a730c5cd74eab4c7164309d810de660fcea3

Maintenance freshness

7/18/2026

Usage

2 downloads · 0 views

File structure

📄 SKILL.md