ClawHub
Back to skill

Security audit

Obsidian Core Notes

Security checks across malware telemetry and agentic risk

Overview

This skill performs disclosed local Obsidian vault indexing and note generation, with no evidence of malware, exfiltration, hidden persistence, or credential use.

Install only if you want local Obsidian-style indexes and sidecar notes. Run scans or refreshes on a specific vault folder, review dry-run output where available, and avoid roots containing secrets or private business material unless generated Markdown previews are acceptable. Use clean-generated cautiously because it deletes marker-bearing generated notes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description is broad enough to trigger during very common file and workspace activities such as creating, editing, moving, deleting, scanning, summarizing, and organizing files. That increases the chance the skill is invoked outside narrowly intended Obsidian maintenance tasks, causing unnecessary wide-scope filesystem operations and automated note generation or modification across a workspace.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The refresh flow generates Markdown notes that embed extracted previews and summaries from files across the workspace, including business documents, code, spreadsheets, and text. In a vault or shared workspace context, this can unintentionally duplicate sensitive content into new, more discoverable Markdown files without explicit user acknowledgement, increasing the chance of accidental disclosure or oversharing.

Missing User Warnings

Medium
Confidence
80% confidence
Finding
The clean-generated command deletes all Markdown files containing the tool's markers immediately when not in dry-run mode, with no interactive confirmation or secondary safety check. If run from the wrong root or against a broader workspace than intended, it can cause irreversible data loss of generated notes and indexes, especially where users may have edited those files after generation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.