Faceswap

Security checks across malware telemetry and agentic risk

Overview

This face-swap skill does what it says, but users should treat uploaded videos, face images, API keys, and generated public links as sensitive.

Install only if you trust verging.ai and its storage path with the specific videos and face images you submit. Use a revocable API key, monitor credit usage, avoid processing people without consent or rights, and treat generated public result URLs and downloaded outputs as sensitive.

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 (1)

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The skill explicitly instructs downloading user-supplied remote media and uploading video and face images to verging.ai/R2, but the operational flow does not require a clear, contextual warning or confirmation at the point of transfer. This can cause users to unintentionally send sensitive media or URLs to third-party infrastructure, creating privacy and data-handling risk, especially because outputs are also described as public URLs.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal