ClawHub
Back to skill

Security audit

Obsidian Remote

Security checks for vulnerabilities and agentic risk

Overview

The skill is not deceptive, but it gives an agent broad live control over Obsidian, including destructive edits, publishing, plugin changes, and developer-tool access without enough guardrails.

Review this skill carefully before installing. It is appropriate only if you want an agent to control your running Obsidian app and vault. Require explicit approval before delete, overwrite, restore, publish, plugin/theme/snippet, restricted-mode, eval, CDP, debugger, DOM, or screenshot commands, and keep backups or sync history available.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (3)

Missing User Warnings

High
Confidence
97% confidence
Finding
The developer-tools section exposes capabilities such as JavaScript evaluation, DOM inspection, console access, debugger attachment, CDP commands, and screenshots without any warning about arbitrary code execution, introspection, and sensitive data exposure. In context, this is especially dangerous because the skill controls a live Obsidian desktop process, so eval or CDP access could inspect vault contents, manipulate the app beyond note editing, or access secrets visible in the UI or plugin state.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This section documents destructive operations such as delete, permanent delete, move/rename, and overwrite-capable create commands without any safety guidance, confirmation expectations, or backup recommendations. In a skill that enables live remote control of a running Obsidian app, these commands can cause irreversible data loss or large-scale unintended modification if invoked by an agent or user mistake.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises plugin installation, enable/disable, uninstall, restricted-mode changes, theme changes, and CSS snippet toggling without warning that these actions alter executable configuration and application behavior. Because this skill provides full remote control of the live desktop app, an agent could weaken security posture, introduce untrusted code via community plugins, or destabilize the user's environment.

Static analysis

No suspicious patterns detected.