ClawHub
Back to skill

Security audit

Obsidian Toolkit Free

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Obsidian note-management skill, but users should be careful because it can move, create, and delete local notes through command-line tools.

Install only if you are comfortable letting an agent run obsidian-cli against your Obsidian vault. Before delete or bulk reorganization, ask for a preview and explicit confirmation, and keep backups or sync history enabled. Treat the local-only claim narrowly: Obsidian files are stored locally, but the agent platform may still process prompts or selected note contents through its configured LLM service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill states that it is fully local and does not involve cloud calls, yet elsewhere declares an LLM API dependency and explicit model routing. This can mislead users about where data may be processed, creating privacy and compliance risk if users assume note contents never leave the local machine.

Intent-Code Divergence

Low
Confidence
89% confidence
Finding
The file header marks the skill as Proprietary while the later license section says the improved work is MIT-licensed. Conflicting license terms create legal ambiguity that can cause unsafe redistribution, compliance failures, or incorrect trust assumptions about reuse rights.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill includes direct destructive deletion commands as part of normal note-management flows without requiring explicit confirmation or a safer default such as trash/archive. In an agent-executed context, this increases the chance of accidental data loss from ambiguous prompts or over-eager automation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.