Obsidian Local REST API

• Outcome: Review
• Latest audit: May 29, 2026 at 9:33 PM UTC
• Version:
  1.1.0

Overview

This Obsidian skill is purpose-aligned, but it gives an agent broad note-reading, note-modifying, deletion, and command-execution authority without clear confirmation guardrails.

Install only if you are comfortable giving the agent API-key access to your Obsidian vault. Before use, narrow the triggers, require confirmation before overwrites, deletes, patches, or command execution, keep the API key scoped and protected, and avoid exposing the REST API beyond trusted local networks.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger list includes very broad phrases such as 'note this', 'create a note', 'append to', and especially 'sv', which can cause the skill to activate in unrelated conversations. Because this skill can read, overwrite, append, delete notes, and execute Obsidian commands, accidental invocation could lead to unintended data access or modification.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill documents destructive and privileged capabilities, including deleting notes and executing arbitrary Obsidian commands, without strong user-facing guardrails such as explicit consent, confirmation, or command allowlisting. In a conversational agent context, this materially increases the chance of unsafe actions being performed from ambiguous or malicious prompts.

VirusTotal

64/64 vendors flagged this skill as clean.