Back to skill

Security audit

Comic To Realistic

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward external AI image-conversion API wrapper, but users should know their image URL and prompt are sent to ngmob.com for processing.

Install only if you are comfortable sending the provided public image URL and prompt to ngmob.com's API. Do not submit private, sensitive, non-consensual, or access-controlled image URLs unless you understand the provider's privacy 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 (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README describes uploading an image URL and prompt to an AI-driven image-processing workflow but does not clearly warn users that their supplied content will be transmitted to an external processing service. This can mislead users about data handling and privacy exposure, especially if they submit private image URLs or sensitive prompts assuming local-only processing.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill asks users to supply a public image URL and names external endpoints for product and API access, but it does not clearly warn that the provided image URL and associated image content will be sent to third-party infrastructure for processing. This creates a privacy and transparency issue because users may unknowingly expose personal or sensitive images, and URL-based ingestion can also reveal metadata or access patterns to external services.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The skill is designed to call an external API endpoint, which means user content and potentially account-linked usage data are transmitted outside the local platform boundary. In an image-generation skill this is contextually expected, but it still creates exposure to third-party data collection, logging, or misuse if not clearly disclosed and governed.

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/ffd6peHk6HRoiCCrpOuQ/run",
  "method": "POST",
  "headers": {
    "Content-Type": "application/json",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest sends user-supplied image URLs and prompts to a third-party API, but the skill description and manifest provide no user-facing disclosure that this content leaves the platform. Images and prompts can contain sensitive personal data, and silent transmission to an external service creates a privacy and data-handling risk even if the API is expected for functionality.

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 · 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}}"

Static analysis

No suspicious patterns detected.