video-inpainting
Edit Video Regions with RunComfy
Video region edits can fail when objects move across frames. This skill routes the task to RunComfy video inpainting workflows and gives clear prompt guidance.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "video-inpainting" from https://skillstore.io/skills/doany-ai-video-inpainting.md and its manifest at https://skillstore.io/api/skills/doany-ai-video-inpainting/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 "video-inpainting". Remove a boom microphone from a short licensed scene.
Expected outcome:
The skill recommends Wan 2-7 Edit-Video, gives a focused preservation prompt, and explains where the edited result will be saved.
Using "video-inpainting". Replace a moving product box in a social clip.
Expected outcome:
The skill suggests a single-change edit pass, warns about drift, and recommends follow-up review for motion consistency.
Using "video-inpainting". Need exact mask tracking for a person crossing the frame.
Expected outcome:
The skill explains that prompt routing is not enough and points to a ComfyUI workflow with mask propagation.
Security Audit
Medium RiskStatic command, network, filesystem, and reconnaissance hits are false positives from Markdown formatting, documentation links, and security notes. No prompt injection attempt or hidden code execution was found, but normal use sends video edit data to RunComfy and includes watermark removal guidance that needs rights-aware safeguards.
Confirmed security concerns (2)
Risk Factors
⚙️ External commands (31)
🌐 Network access (21)
📁 Filesystem access (2)
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/doany-ai-video-inpainting/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-video-inpainting?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-video-inpainting?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-video-inpainting/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-video-inpainting.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
doany-ai. (2026). video-inpainting security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-video-inpainting/audits/4BibTeX citation
@techreport{doany-ai-doany-ai-video-inpainting-2026,
author = {doany-ai},
title = {video-inpainting security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/doany-ai-video-inpainting/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: "video-inpainting security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/doany-ai-video-inpainting/audits/4"
identifiers:
- type: other
value: "skillstore:doany-ai-video-inpainting:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
3 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
agentspace-so-video-inpainting
2026-08-21
runcomfy-com-video-inpainting
2026-08-21
doany-ai-video-inpainting
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Clean Licensed Footage
Remove a temporary object, cable, or background distraction from footage you own or are authorized to edit.
Test Product Region Changes
Replace a simple product area in a short clip while preserving motion and surrounding content.
Choose an Inpainting Route
Compare Wan, Lucy, Seedream, and ComfyUI options before running a video region edit.
Try These Prompts
Use video-inpainting on this video URL. Remove the small object near the lower left across all frames. Preserve all other content.
Edit the selected video region with RunComfy. Replace the red cup on the table with a blue cup. Keep lighting and motion consistent.
Review this video edit request and choose the best RunComfy route. Explain whether Wan, Lucy, Seedream, or ComfyUI fits best.
Plan a video inpainting workflow for exact mask propagation. Include route choice, expected quality checks, and when to use ComfyUI.
Best Practices
- Use only media you own or have clear permission to edit.
- Describe one region and one edit per run for better consistency.
- Use ComfyUI workflows when exact masks or temporal tracking are required.
Avoid
- Do not remove watermarks or logos from media without authorization.
- Do not combine many unrelated edits in one prompt-driven run.
- Do not treat prompt-only edits as pixel-accurate mask propagation.