Back to skill

Security audit

MasterPiece Clone

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward image style-transfer API integration, with the main consideration being that user-provided image URLs are sent to a third-party service.

Install only if you are comfortable sending the reference and target image URLs to ngmob.com for processing. Avoid submitting private, sensitive, or access-controlled images unless you understand the provider's handling and retention practices.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (8)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the operator to submit user-supplied image URLs to a third-party API without any privacy, consent, retention, or data-handling warning. Even if only URLs are sent, the external service can fetch and process the referenced images, which may expose private or sensitive user content to an unvetted external processor.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

The base URL match at the same line reflects the same external transmission event rather than a distinct additional issue. It is still a valid concern because it confirms reliance on an external API endpoint for handling user-provided content.

Content

Scanner excerpt · Skills.md (reported line 70)May include surrounding context.

md
"Image Input": "https://example.com/reference-style.png",
    "Image Input 1": "https://example.com/target-photo.png"
  }
}' | curl -X POST https://api.ngmob.com/api/v1/workflows/Awtk0EnhqBGkoOExvseI/run \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d @-

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

The base URL match at the same line reflects the same external transmission event rather than a distinct additional issue. It is still a valid concern because it confirms reliance on an external API endpoint for handling user-provided content.

Content

Scanner excerpt · Skills.md (reported line 70)May include surrounding context.

md
"Image Input": "https://example.com/reference-style.png",
    "Image Input 1": "https://example.com/target-photo.png"
  }
}' | curl -X POST https://api.ngmob.com/api/v1/workflows/Awtk0EnhqBGkoOExvseI/run \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d @-

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill accepts user-supplied image URLs and transmits them to a third-party API for processing, but the manifest provides no user-facing disclosure about external sharing, retention, or privacy implications. Because images may contain sensitive personal data or internal URLs, this creates a real privacy and data-handling risk even if the transmission is necessary for functionality.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The manifest is configured to send request data to an external service at api.ngmob.com, which means user-provided image references leave the local trust boundary. In an image-processing skill this may be functionally required, but without explicit transparency, validation, or data-governance controls, external transmission of user content is still a security and privacy concern.

Content

Scanner excerpt · manifest.json (reported line 9)May include surrounding context.

json
"author": "your-name",
  "type": "api",
  "category": "image-generation",
  "endpoint": "https://api.ngmob.com/api/v1/workflows/Awtk0EnhqBGkoOExvseI/run",
  "method": "POST",
  "headers": {
    "Content-Type": "application/json",

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · Skills.md (reported line 81)May include surrounding context.

md
],
  "polling": {
    "enabled": true,
    "url": "https://api.ngmob.com/api/v1/workflows/executions/{{task_id}}",
    "method": "GET",
    "headers": {
      "Authorization": "Bearer {{API_KEY}}"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · manifest.json (reported line 44)May include surrounding context.

json
],
  "polling": {
    "enabled": true,
    "url": "https://api.ngmob.com/api/v1/workflows/executions/{{task_id}}",
    "method": "GET",
    "headers": {
      "Authorization": "Bearer {{API_KEY}}"

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README instructs users to upload personal photos for AI transformation but provides no notice about privacy, retention, sharing, or third-party processing. While this is not an exploit in itself, it can mislead users into submitting sensitive images without informed consent, increasing privacy and compliance risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.