image-inpainting
Edit Images with Masked Inpainting
Precise local image edits are hard when only one region should change. This skill routes masked images through RunComfy inpainting models and suggests fallback edit models when no mask exists.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "image-inpainting" from https://skillstore.io/skills/doany-ai-image-inpainting.md and its manifest at https://skillstore.io/api/skills/doany-ai-image-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 "image-inpainting". A masked product photo has a cluttered shelf behind the subject.
Expected outcome:
- The skill selects Z-Image Turbo Inpainting because a mask exists.
- It recommends a high strength setting for a full background replacement.
- The result should preserve the product edges and replace only the masked shelf.
Using "image-inpainting". A portrait has a small masked blemish on one cheek.
Expected outcome:
The skill recommends low strength cleanup and preservation language for skin tone, texture, lighting, and nearby facial features.
Using "image-inpainting". The user has no mask and asks to remove a described object.
Expected outcome:
The skill recommends a description-based edit model and asks for spatial details before running the edit.
Security Audit
Medium RiskMost static findings are Markdown formatting, documentation links, or model-selection text rather than executable code. I found no prompt injection evidence. The skill sends user image and mask URLs to RunComfy and promotes watermark removal, so authorization boundaries are needed.
Confirmed security concerns (2)
Risk Factors
⚙️ External commands (47)
🌐 Network access (23)
📁 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-image-inpainting/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-image-inpainting?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-image-inpainting?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-image-inpainting/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-image-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). image-inpainting security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-image-inpainting/audits/4BibTeX citation
@techreport{doany-ai-doany-ai-image-inpainting-2026,
author = {doany-ai},
title = {image-inpainting security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/doany-ai-image-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: "image-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-image-inpainting/audits/4"
identifiers:
- type: other
value: "skillstore:doany-ai-image-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
runcomfy-com-image-inpainting
2026-08-21
doany-ai-image-inpainting
2026-08-21
agentspace-so-image-inpainting
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Retouch Product Photos
Replace a masked background while keeping the product, shadows, and edges consistent.
Clean Local Image Defects
Fill a masked scratch, blemish, or damaged area without changing the rest of the image.
Choose the Correct Edit Route
Decide whether a masked inpainting model or description-based edit model fits the request.
Try These Prompts
Use the image-inpainting skill to remove the object covered by my mask. Preserve lighting, texture, and all unmasked areas.
Use Z-Image Turbo Inpainting for this image and mask. Replace only the masked background with a light gray studio backdrop.
Plan a RunComfy inpainting request for this image, mask, and edit goal. Recommend strength, control scale, and preservation language first.
Compare the mask-driven and description-based routes for this edit. Select the model, explain why, then run the chosen RunComfy workflow.
Best Practices
- Use image and mask URLs that the user explicitly provided for this edit.
- Soften mask edges slightly and describe what must stay unchanged.
- Start with lower strength for cleanup and increase only for full replacement.
Avoid
- Running edits on images the user did not provide or authorize.
- Using a broad mask when only a small region should change.
- Treating description-based fallback as pixel-precise when a mask is required.