image-inpainting
Inpaint Images with RunComfy
Precise image edits are hard when only one region should change. This skill routes Claude, Codex, or Claude Code to RunComfy inpainting models with mask-aware prompts and safe CLI usage.
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/agentspace-so-image-inpainting.md and its manifest at https://skillstore.io/api/skills/agentspace-so-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 user provides a street photo and a cable mask, then asks to remove only the overhead cables.
Expected outcome:
- The skill selects Z-Image Turbo Inpainting because a mask is available.
- It prepares a prompt that preserves rooflines and sky gradients.
- It runs the job through the runcomfy CLI and saves outputs to the chosen directory.
Using "image-inpainting". A user has no mask but wants the bottom-right label removed from an image they own.
Expected outcome:
- The skill chooses a description-based edit model.
- It writes a spatial instruction that targets only the bottom-right label.
- It reminds the user to confirm they are authorized to remove the mark.
Using "image-inpainting". A product team wants a masked background changed to a neutral studio backdrop.
Expected outcome:
- The skill recommends high strength for full background replacement.
- It preserves product edges and lighting in the prompt.
- It uses the supplied image and mask URLs for the RunComfy request.
Security Audit
Medium RiskMost static findings are false positives caused by Markdown backticks, documentation links, placeholder URLs, and explanatory text. The real security surface is limited to intentional runcomfy CLI execution and outbound uploads to RunComfy, plus a semantic misuse risk from explicit watermark-removal guidance.
Confirmed security concerns (1)
Capability review items (4)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
โ๏ธ External commands (47)
๐ Network access (23)
๐ 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/agentspace-so-image-inpainting/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/agentspace-so-image-inpainting?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/agentspace-so-image-inpainting?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentspace-so-image-inpainting/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/agentspace-so-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 ยท BibTeX ยท CFF)
APA citation
agentspace-so. (2026). image-inpainting security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/agentspace-so-image-inpainting/audits/7BibTeX citation
@techreport{agentspace-so-agentspace-so-image-inpainting-2026,
author = {agentspace-so},
title = {image-inpainting security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/agentspace-so-image-inpainting/audits/7},
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 7)"
version: "unspecified"
type: report
authors:
- name: "agentspace-so"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/agentspace-so-image-inpainting/audits/7"
identifiers:
- type: other
value: "skillstore:agentspace-so-image-inpainting:audit:7"
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
Clean product photos
Replace a masked background or remove a small defect while preserving the product shape and lighting.
Repair image regions
Fill a damaged or empty area using a mask and a prompt that describes the desired replacement.
Localize visual edits
Use description-based editing when a mask is not available but the target region can be named clearly.
Try These Prompts
Inpaint this image using the provided mask. Remove the masked object and preserve the background texture, lighting, and perspective.
Use the mask to replace only the background with smooth light gray studio paper. Preserve the product edges, shadows, and color.
I have an image and this edit goal, but I am not sure if my mask is good enough. Choose the best RunComfy inpainting or edit route and explain the needed inputs.
Run an inpainting job for this masked region. Use a lower strength for subtle repair, set control scale for edge preservation, and include a reproducible seed.
Best Practices
- Use a clean grayscale mask where white marks the region to change and black marks the region to preserve.
- Name the surrounding details that must stay unchanged in every prompt.
- Use only images and marks you own or have permission to edit.
Avoid
- Do not use a vague prompt that fails to describe what should remain unchanged.
- Do not reuse a mask from a different source image.
- Do not submit private or regulated images unless remote processing is approved.
Frequently Asked Questions
Does this skill create masks?
Which model is used by default?
Can it edit images without a mask?
Does it work offline?
Where are results saved?
Is it safe for confidential images?
Developer Details
Author
agentspace-soLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
1ffa7643651792ccb4bd3b15d924d2c97edff755
Maintenance freshness
7/21/2026
Usage
4 downloads ยท 59 views
File structure
๐ SKILL.md