ClawHub

Gbrain Obsidian Vault

Security checks across malware telemetry and agentic risk

Overview

This skill locally connects an OpenClaw/gbrain wiki to Obsidian and its file changes are disclosed and aligned with that purpose.

Install this only if you use Obsidian with gbrain/OpenClaw memory. Review the setup script first, back up existing .obsidian settings if you care about them, and be aware that optional gbrain export writes markdown files into your vault.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill advertises several broad natural-language trigger phrases such as '第二大脑可视化', 'memory 图谱', and 'second brain vault' that are not tightly scoped to a single concrete operation. In an agent environment, overly generic triggers can cause unintended activation in loosely related conversations, leading the agent to suggest or perform filesystem, symlink, gitignore, or export setup steps in the wrong context.

Missing User Warnings

Medium
Confidence
81% confidence
Finding
The document promotes file-writing and export behavior into a live Obsidian vault without warning users that local markdown content may be created, modified, or overwritten. In a skill that bridges memory, graph exports, and automated sync/embed workflows, unclear write semantics can lead to unintended data changes, vault corruption, or privacy exposure if users assume the process is passive or read-only.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal