Back to skill

Security audit

Virtual Try On

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently sends user-provided clothing image URLs to a disclosed external virtual try-on API to generate product photos.

Install only if you are comfortable sending the clothing image URLs you provide to api.ngmob.com for processing. Avoid private, access-controlled, signed, confidential, or regulated image URLs unless you have authorization and accept the provider's data handling.

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 (7)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs users to send clothing image URLs to a third-party API but does not clearly warn that user-provided images and URLs are transmitted off-platform for external processing. This can lead to privacy, confidentiality, and compliance issues if users provide proprietary product images, pre-release designs, or personal images without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The hardcoded external endpoint indicates that workflow execution depends on a third-party service outside the platform's trust boundary. If users provide internal, confidential, or access-controlled image links, those references may be exposed to the external provider and could enable unauthorized retrieval or retention of sensitive assets.

Content

Scanner excerpt · Skills.md (reported line 71)May include surrounding context.

2. Call the Workflow API

bash
curl -X POST https://api.ngmob.com/api/v1/workflows/2IIk3Z6NKuPZP7moonEI/run \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The hardcoded external endpoint indicates that workflow execution depends on a third-party service outside the platform's trust boundary. If users provide internal, confidential, or access-controlled image links, those references may be exposed to the external provider and could enable unauthorized retrieval or retention of sensitive assets.

Content

Scanner excerpt · Skills.md (reported line 71)May include surrounding context.

2. Call the Workflow API

bash
curl -X POST https://api.ngmob.com/api/v1/workflows/2IIk3Z6NKuPZP7moonEI/run \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest transmits user-supplied clothing image URLs to a third-party API, but the skill description and schema do not disclose that user data will be sent off-platform. Even if the inputs are described as publicly accessible URLs, they can still reveal business-sensitive assets, user intent, or link to infrastructure the user controls, creating a privacy and data-handling risk.

Content

No source excerpt is available for this finding.

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 89)May include surrounding context.

md
"author": "your-name",
  "type": "api",
  "category": "image-generation",
  "endpoint": "https://api.ngmob.com/api/v1/workflows/2IIk3Z6NKuPZP7moonEI/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 · 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/2IIk3Z6NKuPZP7moonEI/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 · manifest.json (reported line 58)May include surrounding context.

json
"author": "your-name",
  "type": "api",
  "category": "image-generation",
  "endpoint": "https://api.ngmob.com/api/v1/workflows/2IIk3Z6NKuPZP7moonEI/run",
  "method": "POST",
  "headers": {
    "Content-Type": "application/json",

Static analysis

No suspicious patterns detected.