Skills image-edit
📦

image-edit

Content revision r2 High Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Edit Images Through a Hosted Agent Workflow

Image editing often requires provider accounts, local models, and separate billing. This skill guides hosted edits with cost limits, durable assets, and recoverable jobs.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "image-edit" from https://skillstore.io/skills/danielgwilson-image-edit.md and its manifest at https://skillstore.io/api/skills/danielgwilson-image-edit/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/danielgwilson-image-edit.md Signed manifest GET /api/skills/danielgwilson-image-edit/manifest Signed lockfile GET /api/skills/danielgwilson-image-edit/lockfile

Test it

Using "image-edit". Replace the office background with a neutral studio wall while keeping the person unchanged.

Expected outcome:

The edit completed with a durable hosted asset, recoverable job reference, and cost receipt.

Using "image-edit". Repair the damaged corner of this product photo and preserve all printed labels.

Expected outcome:

The repaired image preserves the labels and matches the surrounding surface, lighting, and perspective.

Using "image-edit". Create a watercolor variation and keep the composition suitable for a square social post.

Expected outcome:

The variation applies a watercolor treatment while retaining the subject placement and square composition.

Security Audit

High Risk
v8 • 7/23/2026 Open versioned report

Twelve static findings are confirmed because the workflow executes remote packages, accepts a server-provided command, contacts a hosted API, and writes hidden agent state. Twelve findings are false positives involving Markdown formatting or documentation links, while semantic review also identifies hosted image persistence and diagnostic data disclosure.

1
Files scanned
79
Lines analyzed
12
Review items
0
False positives ignored

Confirmed security concerns (2)

High
SKILL.md:4SKILL.md:24SKILL.md:28
Third-Party Image Upload and Persistence
The skill uploads or reuses input images and keeps generated work as durable hosted media. Sensitive images may leave the device and remain accessible.
The skill explicitly says to upload images, return durable hosted URLs, and keep generated work in Luxin.
Medium
SKILL.md:78
Diagnostic Feedback Can Disclose Task Data
The feedback instruction sends attempted commands, expected behavior, and actual behavior. Those fields may include private prompts, identifiers, or operational details.
Line 78 explicitly specifies the command and behavior fields to include in hosted feedback.
Capability review items (12)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

High
SKILL.md:28
Ruby/shell backtick execution
Do not bring provider API keys, create provider accounts, run a local model server, or wire a separa
The skill instructs the agent to execute data.next_command supplied by a hosted response. A compromised service could return an unsafe command.
High
SKILL.md:32-34
Ruby/shell backtick execution
```bash
The Bash block runs npx with luxin-cli@latest and automatic approval. This executes mutable remote package code without a version pin.
High
SKILL.md:38-40
Ruby/shell backtick execution
```bash
The Bash block executes the mutable luxin-cli@latest package and submits an image editing request to its hosted runtime.
High
SKILL.md:46-48
Ruby/shell backtick execution
```bash
The command runs npx to install a remote GitHub skill globally with automatic confirmation. This changes persistent agent configuration.
High
SKILL.md:52-54
Ruby/shell backtick execution
```bash
The command runs an automatically confirmed global installation from a remote GitHub repository. The source is not pinned to an immutable commit.
High
SKILL.md:62-67
Ruby/shell backtick execution
```bash
The Bash block changes HOME and CODEX_HOME, creates hidden directories, and runs a remote global installer without interactive approval.
Medium
SKILL.md:67-78
Ruby/shell backtick execution
```
Line 78 directs the agent to run a Luxin feedback command that transmits attempted commands and observed behavior to the hosted service.
Medium
SKILL.md:59
Hidden file access
`$HOME/.agents`; `CODEX_HOME` keeps Codex profile state on the same writable
The text states that the installer writes to $HOME/.agents. This modifies hidden, persistent agent configuration outside the current project.
Medium
SKILL.md:63
Hidden file access
export HOME="$PWD/.agent-home"
The command redirects HOME to a hidden workspace directory. Subsequent tools can write profile state or credentials into the project tree.
Medium
SKILL.md:64
Hidden file access
export CODEX_HOME="$HOME/.codex"
The command places CODEX_HOME in a hidden workspace directory. Codex state or credentials could enter backups or version control.
Low
SKILL.md:11
Hardcoded URL
canonical_api_url: https://api.luxin.sh
This is the operational endpoint for the hosted runtime. Image editing requests and related data leave the local environment through this API.
Low
SKILL.md:76
Hardcoded URL
- Hosted API: https://api.luxin.sh
The listed URL is the hosted API used by the workflow. Requests can carry user images, prompts, and job metadata off-device.

Risk Factors

⚙️ External commands (13)
SKILL.md:24 SKILL.md:28 SKILL.md:32-34 SKILL.md:34-38 SKILL.md:38-40 SKILL.md:40-46 SKILL.md:46-48 SKILL.md:48-52 SKILL.md:52-54 SKILL.md:54-59 SKILL.md:59 SKILL.md:62-67 SKILL.md:67-78
🌐 Network access (8)
SKILL.md:5 SKILL.md:6 SKILL.md:10 SKILL.md:11 SKILL.md:73 SKILL.md:74 SKILL.md:75 SKILL.md:76
📁 Filesystem access (3)
SKILL.md:59 SKILL.md:63 SKILL.md:64
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
Security Assessment

Copy report link

https://skillstore.io/skills/danielgwilson-image-edit/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/danielgwilson-image-edit/security.svg)](https://skillstore.io/skills/danielgwilson-image-edit?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/danielgwilson-image-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

danielgwilson. (2026). image-edit security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/danielgwilson-image-edit/audits/8

BibTeX citation

@techreport{danielgwilson-danielgwilson-image-edit-2026, author = {danielgwilson}, title = {image-edit security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/danielgwilson-image-edit/audits/8}, 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-edit security audit report (audit version 8)" version: "unspecified" type: report authors: - name: "danielgwilson" date-released: "2026-07-23" url: "https://skillstore.io/skills/danielgwilson-image-edit/audits/8" identifiers: - type: other value: "skillstore:danielgwilson-image-edit:audit:8" description: "Skillstore immutable audit report identifier"

Compare variants

4 installable variants

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

Why this variant is first

Higher Skillstore usage
runcomfy-com Recommended

runcomfy-com-image-edit

Skillstore Score 50
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

doany-ai

doany-ai-image-edit

Skillstore Score 50
Evidence Confidence High
Skillstore usage 7
Updated

2026-08-21

agentspace-so

agentspace-so-image-edit

Skillstore Score 38
Evidence Confidence High
Skillstore usage 9
Updated

2026-08-21

danielgwilson Current

danielgwilson-image-edit

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 6
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
67
Community
83
Spec Compliance

What You Can Build

Revise Campaign Artwork

Replace backgrounds or repair details while preserving the main subject and controlling estimated cost.

Produce Product Variations

Create controlled visual variations from an existing product image for review or testing.

Automate Image Repairs

Run repeatable image edits with structured job records and durable output references.

Try These Prompts

Simple Background Change 
Edit this image by replacing the background with [setting]. Keep the subject, pose, lighting direction, and proportions unchanged.
Controlled Restyle 
Restyle this image as [style]. Preserve [elements], avoid [changes], and keep the final composition suitable for [use].
Targeted Repair 
Repair [problem area] without changing [protected areas]. Match the surrounding texture, color, lighting, and perspective.
Production Edit Specification 
Transform [input] for [channel]. Preserve [requirements], change [details], enforce [policy constraints], and keep estimated cost below [amount].

Best Practices

  • State the exact area to change and list elements that must remain unchanged.
  • Run the no-spend guide before creation and set a strict estimated cost limit.
  • Obtain consent before uploading images and review the hosted service retention policy.

Avoid

  • Do not execute a server-provided command without inspecting every argument.
  • Do not upload confidential images without authorization and an approved retention plan.
  • Do not use mutable latest packages in unattended or privileged environments.

Frequently Asked Questions

Does this skill require a local image model?
No. It uses the hosted Luxin runtime and does not require a local model server.
Do I need provider API credentials?
No provider credentials are required. Luxin may use an optional restricted hosted token.
Can it edit an existing image?
Yes. The main workflow accepts an existing image identifier, an edit model, and a natural-language prompt.
How are costs controlled?
Use the no-spend guide first, then set a maximum estimated cost per image before creation.
Where are edited images stored?
The workflow returns durable hosted media URLs. Review Luxin retention and deletion terms before uploading sensitive images.
Can failed jobs be investigated?
Yes. Jobs are designed to be recoverable, and the skill provides a hosted feedback command for missing capabilities.

Developer Details

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Repository

https://github.com/danielgwilson/image-skill-cli/tree/main/skills/image-edit

Ref

c43861a65bb95efcae259cd161c9d6f4dc7eec6f

Maintenance freshness

7/24/2026

Usage

2 downloads · 0 views

File structure

📄 SKILL.md