Obsidian笔记助手

Security checks across malware telemetry and agentic risk

Overview

This Obsidian helper is a straightforward note-management skill that clearly centers on local Markdown vault reads and writes, with no hidden installer, networking, credential use, or persistence.

Install only if you are comfortable letting the agent read and modify your Obsidian vault. Before using write actions, confirm the vault path and target filenames, preview generated content, and keep normal backups for important notes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation phrases ("Obsidian / 笔记 / 知识库 / 双向链接") are broad enough that ordinary conversation about notes or knowledge bases could unintentionally trigger the skill. Because the skill includes file-reading and file-writing behaviors against a local vault, accidental activation can lead to unintended modification or disclosure of note contents.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly performs direct writes to Markdown files in the Obsidian vault but does not present an explicit warning or consent step about modifying user data. In this context, silent write capability is risky because a user may invoke the skill expecting read-only assistance while the skill creates or overwrites notes in a personal knowledge base.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal