Image Editing

• Outcome: Pass
• Latest audit: May 28, 2026, 12:34 PM
• Version:
  1.0.0

Overview

This is a coherent image-editing guide, but some examples send selected images to third-party AI services.

Install is reasonable for an image-editing reference skill. Before using cloud examples, confirm the image is safe to upload, review provider privacy, retention, billing, and consent requirements, and prefer local tools for confidential photos, IDs, business images, or regulated content.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (20)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill recommends sending user images to third-party background-removal services but does not warn that the image content is transmitted off-device to external vendors. This can expose sensitive, proprietary, or personal images and may create compliance and privacy issues, especially because the skill is specifically about image processing where user uploads are central to operation.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The example uploads a local image and mask to OpenAI's external API, but the documentation does not warn users that image contents leave the local environment. In an image-editing skill, users may reasonably try sensitive photos, documents, or proprietary artwork, so omission of a disclosure can lead to inadvertent data exposure and privacy or compliance issues.

Missing User Warnings

Low

• Confidence: 91% confidence
• Finding: The example sends an image and prompt to OpenAI's external image editing API, but the documentation does not disclose that user content leaves the local environment. This can lead users to submit sensitive images or confidential prompt data without informed consent, which is a real privacy and data-handling risk even though the example is otherwise normal for the skill's purpose.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: This example reads a local image file and sends it to Replicate, a third-party external service, without any warning that user content leaves the local environment. In an image-restoration skill, users may process sensitive face photos, so omission of a privacy/data-transfer notice can lead to unintended disclosure of personal or biometric data.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The old photo restoration sample uploads a local photo to an external model endpoint without disclosing the transmission. Old photos often contain highly sensitive family images and identifiable faces, making silent third-party upload particularly risky in this context.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The colorization example opens a local image and submits it to Replicate without informing users that the file is transmitted off-device. Because this skill targets image editing and restoration workflows, users may reasonably assume processing is local unless warned otherwise, increasing the chance of accidental disclosure.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The document provides multiple examples that upload local image files to third-party APIs but does not clearly warn users that their images, masks, and possibly sensitive visual content are transmitted off-device. In an image-editing skill, users may reasonably supply private photos, documents, IDs, or proprietary artwork, so omission of a privacy/data-transfer notice creates real risk of unintended disclosure.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The Magnific example instructs users to upload a local image file to a third-party cloud API, but it gives no warning that image contents will leave the local environment or be subject to the provider's storage, logging, or retention practices. In an image-editing skill, users may reasonably test with personal, client, or otherwise sensitive photos, so the omission creates a real privacy and data-handling risk even though the example appears educational rather than malicious.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The Replicate code sample opens a local image and sends it to an external hosted model, but the documentation does not disclose that the file is transmitted off-device for remote inference. Because this skill is specifically about editing user-supplied images, the context makes privacy leakage more plausible: users may upload portraits, IDs, medical images, or proprietary artwork without understanding the transmission.

External Transmission

Medium

• Category: Data Exfiltration

Content

```python
import requests

response = requests.post(
    "https://api.remove.bg/v1.0/removebg",
    files={"image_file": open("photo.jpg", "rb")},
    data={"size": "auto"},

• Confidence: 94% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

```python
import requests

response = requests.post(
    "https://clipdrop-api.co/remove-background/v1",
    files={"image_file": open("photo.jpg", "rb")},
    headers={"x-api-key": "YOUR_API_KEY"}

• Confidence: 93% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

### Photoroom API

```python
response = requests.post(
    "https://sdk.photoroom.com/v1/segment",
    files={"image_file": open("photo.jpg", "rb")},
    headers={"x-api-key": "YOUR_API_KEY"}

• Confidence: 92% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

### remove.bg (API)

```bash
curl -X POST "https://api.remove.bg/v1.0/removebg" \
  -H "X-Api-Key: YOUR_API_KEY" \
  -F "image_file=@photo.jpg" \
  -F "size=auto" \

• Confidence: 91% confidence
• Finding: https://api.remove.bg/

External Transmission

Medium

• Category: Data Exfiltration

Content

import requests

response = requests.post(
    "https://api.remove.bg/v1.0/removebg",
    files={"image_file": open("photo.jpg", "rb")},
    data={"size": "auto"},
    headers={"X-Api-Key": "YOUR_API_KEY"}

• Confidence: 90% confidence
• Finding: https://api.remove.bg/

External Transmission

Medium

• Category: Data Exfiltration

Content

```python
import requests

response = requests.post(
    "https://api.stability.ai/v1/generation/stable-diffusion-xl-1024-v1-0/image-to-image",
    headers={"Authorization": f"Bearer {API_KEY}"},
    files={"init_image": open("image.png", "rb")},

• Confidence: 91% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

import requests

# Background removal
response = requests.post(
    "https://clipdrop-api.co/remove-background/v1",
    headers={"x-api-key": API_KEY},
    files={"image_file": open("photo.jpg", "rb")}

• Confidence: 93% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

)

# Cleanup (remove objects)
response = requests.post(
    "https://clipdrop-api.co/cleanup/v1",
    headers={"x-api-key": API_KEY},
    files={

• Confidence: 94% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

)

# Relight
response = requests.post(
    "https://clipdrop-api.co/relight/v1",
    headers={"x-api-key": API_KEY},
    files={"image_file": open("photo.jpg", "rb")},

• Confidence: 92% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

### remove.bg

```python
response = requests.post(
    "https://api.remove.bg/v1.0/removebg",
    headers={"X-Api-Key": API_KEY},
    files={"image_file": open("photo.jpg", "rb")},

• Confidence: 93% confidence
• Finding: requests.post( "https://

External Transmission

Medium

• Category: Data Exfiltration

Content

### Magnific AI

```bash
curl -X POST "https://api.magnific.ai/v1/upscale" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "image=@photo.jpg" \
  -F "scale=2"

• Confidence: 90% confidence
• Finding: https://api.magnific.ai/

VirusTotal

64/64 vendors flagged this skill as clean.