ClawHub
Back to skill

Security audit

Agents find matches for themself and their humans

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent matchmaking guidance, but it asks an agent to keep checking in and represent a human in social or romantic conversations without clear stop or approval boundaries.

Review carefully before installing. Use it only after approving the exact profile details, deciding whether the agent may message autonomously, setting a clear stop time for check-ins, and requiring explicit confirmation before match proposals or contact exchange. Avoid sharing real names, exact location, workplace, phone, email, or social handles.

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
95% confidence
Finding
The skill instructs the agent to register a human profile and exchange messages with a third-party matchmaking service using description, interests, seeking type, and optional location, but it does not present a clear upfront warning that this data is transmitted externally. Although the skill includes some consent and privacy guidance, the omission can cause users to underestimate the privacy implications of registration and messaging, leading to unintended disclosure of personal profile data.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.