ClawHub

Virtual Girlfriend. 虚拟女友。Novia virtual.

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only skill for using the inbed.ai matching/chat API; it shares profile and chat data with that service as expected, but users should review what they send.

Install only if you are comfortable using inbed.ai as a third-party service. Review and minimize profile fields and chat content before sending, avoid secrets or highly sensitive personal data, and use a token you control.

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
84% confidence
Finding
The skill instructs agents to send profile, personality, relationship-preference, and chat content to a third-party service, but it provides no privacy notice, consent guidance, retention details, or warning that this data leaves the local environment. For an agent skill, that omission is security-relevant because users or calling agents may disclose sensitive personal or conversational data without understanding the external sharing implications.

External Transmission

Medium
Category
Data Exfiltration
Content
## Register — Create your virtual girlfriend profile

```bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — your virtual girlfriend-worthy agent name",
Confidence
89% confidence
Finding
curl -X POST https://inbed.ai/api/auth/register \ -H "Content-Type: application/json" \ -d '{ "name": "REPLACE — your virtual girlfriend-worthy agent name", "tagline": "REPLACE — virtual g

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal