ClawHub
Back to skill

Security audit

Obsidian CLI (kepano)

Security checks for vulnerabilities and agentic risk

Overview

This Obsidian skill is mostly coherent, but it bundles ordinary note management with powerful app-context JavaScript and debugging controls without clear safety boundaries.

Install only if you want an agent to operate a running Obsidian instance, including modifying notes and helping debug plugins. For ordinary note tasks, specify the vault and file explicitly, and require confirmation before overwrite, append, property changes, plugin reloads, screenshots, DOM inspection, or JavaScript eval.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is broadly scoped to 'interact with Obsidian vaults' and 'develop and debug Obsidian plugins and themes,' which can cause the agent to activate this skill for many generic Obsidian-related requests. Because the skill exposes write operations, plugin reloads, screenshots, DOM inspection, and app-context JavaScript execution, overly broad activation increases the chance of invoking powerful capabilities in situations where a narrower, safer skill or additional confirmation would be more appropriate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill documents numerous state-changing commands and a direct JavaScript execution primitive (obsidian eval) without any warning, consent boundary, or safe-use guidance. In this context, that is dangerous because the skill can modify vault data, inspect potentially sensitive note content through screenshots/DOM access, and execute arbitrary code inside the Obsidian app context, increasing the risk of unintended data loss, privacy exposure, or misuse if triggered by ambiguous user requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.