ClawHub
Back to skill

Security audit

Obsidian Search

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Obsidian note-search connector with read-only retrieval, but users should be mindful that it can access full note contents through a third-party index.

Install only if you are comfortable syncing your Obsidian vault to Obvec and letting your agent search and display note contents. Treat the MCP URL as a password, regenerate it if exposed, and ask the agent to confirm before opening full note bodies for ambiguous requests.

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
  • 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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description includes broad trigger phrases such as 'search my notes', 'find in Obsidian', 'what did I write about', and 'related notes', which can overlap with ordinary conversation and cause the skill to activate when the user did not clearly intend to query this connector. Because the skill can retrieve full note content from a third-party-backed note index, accidental invocation may expose sensitive personal or work notes beyond the user's immediate intent.

Static analysis

No suspicious patterns detected.