nano-banana-edit
Edit Images with Nano Banana on RunComfy
Image edits often drift when prompts are vague or batch settings change. This skill gives Claude, Codex, and Claude Code a clear RunComfy workflow for controlled Nano Banana edits.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "nano-banana-edit" from https://skillstore.io/skills/doany-ai-nano-banana-edit.md and its manifest at https://skillstore.io/api/skills/doany-ai-nano-banana-edit/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 "nano-banana-edit". A user provides one portrait URL and asks for a background swap.
Expected outcome:
The assistant selects Nano Banana Edit, preserves the subject, creates a RunComfy edit request, and saves the generated images.
Using "nano-banana-edit". A marketer provides several product URLs and asks for matching gallery images.
Expected outcome:
The assistant prepares one batch edit with consistent framing, locked dimensions, and a shared studio background instruction.
Using "nano-banana-edit". A designer asks to remove one object without changing the rest of the scene.
Expected outcome:
The assistant writes a spatially constrained edit request that names the target object and protects the unchanged areas.
Security Audit
Medium RiskThe skill is a Markdown guide for using RunComfy Nano Banana 2 Edit through a local CLI. Most static findings are Markdown formatting, placeholder URLs, or transparent security notes; the real risks are intentional external CLI execution and third-party image processing. No prompt injection attempt or malicious exfiltration instruction was found.
Confirmed security concerns (1)
Capability review items (9)
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
⚙️ External commands (36)
🌐 Network access (7)
📁 Filesystem access (5)
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-nano-banana-edit/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-nano-banana-edit?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-nano-banana-edit?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-nano-banana-edit/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-nano-banana-edit.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). nano-banana-edit security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-nano-banana-edit/audits/6BibTeX citation
@techreport{doany-ai-doany-ai-nano-banana-edit-2026,
author = {doany-ai},
title = {nano-banana-edit security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/doany-ai-nano-banana-edit/audits/6},
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: "nano-banana-edit security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/doany-ai-nano-banana-edit/audits/6"
identifiers:
- type: other
value: "skillstore:doany-ai-nano-banana-edit:audit:6"
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-nano-banana-edit
2026-08-21
doany-ai-nano-banana-edit
2026-08-21
agentspace-so-nano-banana-edit
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Refresh Product Galleries
Batch edit product photos with consistent framing, backgrounds, resolution, and aspect ratio.
Create Campaign Variants
Generate controlled background, palette, or layout variants while preserving the main subject.
Automate Image Edit Requests
Convert explicit image edit asks into a repeatable RunComfy CLI workflow with known options.
Try These Prompts
Use Nano Banana Edit on this public image URL. Keep the person, clothing, pose, and framing unchanged. Replace only the background with a clean studio wall.
Edit these product image URLs as one batch. Keep each product shape and camera angle unchanged. Use a soft gray studio sweep for every image.
Use Nano Banana Edit to remove only the object in the upper right. Keep the table, lighting, shadows, and other objects unchanged.
Create four controlled variants from this source image. Preserve subject identity and framing. Change only the background color and keep the same aspect ratio.
Best Practices
- State what must stay unchanged before describing the edit.
- Lock aspect ratio and resolution when editing batches.
- Use small edit steps when identity, brand, or composition must remain stable.
Avoid
- Do not combine many unrelated edits in one prompt.
- Do not use private or sensitive image URLs without explicit approval.
- Do not enable web search unless the task needs external visual grounding.