Back to skill

Security audit

Mog Rating Preview

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it uploads a user-provided selfie to MogScore for a face-rating preview, but users should understand the privacy implications first.

Install only if you are comfortable sending the selected face photo to MogScore for processing. Use photos you have the right to submit, avoid sensitive or non-consensual images, and do not change the base URL unless you intentionally want to send the image somewhere else.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to upload a user's face photo to an external website and capture the resulting report, but it does not explicitly warn that the image will be transmitted to a third-party service and may be processed or retained there. Because face photos are highly sensitive biometric-related data, missing notice and consent language creates a real privacy and data-handling risk even if the workflow is otherwise intended and authorized.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script automatically uploads a user-provided face image to a remote service and submits it for processing without any in-script disclosure, consent checkpoint, or confirmation prompt. Because facial images are highly sensitive biometric data, silent transmission to an external website can create privacy, compliance, and user-expectation risks if the surrounding agent invokes this flow without making the transfer explicit.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.