ClawHub

Higgsfield Soul ID

Security checks across malware telemetry and agentic risk

Overview

This skill has a clear purpose, but it should be reviewed because it can install a remote CLI and upload face photos to create a reusable Higgsfield identity model without clear consent or privacy safeguards.

Before installing, verify the Higgsfield CLI through a trusted source instead of blindly running the embedded installer. Only upload face photos of yourself or someone who has explicitly consented, confirm the intended Higgsfield account and paid-plan impact, and review Higgsfield's retention and deletion options for trained Soul models.

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
93% confidence
Finding
The skill processes highly sensitive biometric data (face photos) and explicitly states that local paths are auto-uploaded by the CLI, but it does not clearly warn the user before collection/submission that their photos will be sent to a remote third-party service for model training. In this context, the omission can undermine informed consent and lead users to disclose biometric data without understanding the privacy implications.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This guide instructs users how to upload face photos for identity training but does not warn about the privacy, biometric, and consent risks of submitting personal facial images. Because the skill is explicitly for creating an identity-faithful model of a real person, omission of a privacy warning can lead users to share sensitive biometric data without understanding retention, misuse, or downstream generation risks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal