ClawHub
Back to skill

Security audit

知识库同步引擎

Security checks across malware telemetry and agentic risk

Overview

This skill is purpose-aligned for Obsidian syncing, but it recommends automated Git operations that can modify and push a user's notes without strong confirmation safeguards.

Review before installing if your Obsidian vault contains private notes. Only run the Git workflows on a confirmed vault path, inspect .gitignore first, verify the remote repository, and avoid enabling the cron or Task Scheduler automation unless you are comfortable with recurring automatic commits and pushes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list is very broad and includes common terms like 'obsidian', 'sync', 'git', and '冲突', making accidental invocation during ordinary note-taking or troubleshooting conversations likely. Because this skill has exec capability and contains repository-modifying workflows, unintended activation increases the chance of unreviewed file changes or sync actions being proposed or executed in the wrong context.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill defines an automated sync script that performs git pull, add, commit, and push against a user repository, but the document does not place a prominent upfront warning about destructive or side-effecting behavior before these workflows. In an agent context with exec enabled, this can cause unintended repository mutations, data propagation to remotes, or conflict handling actions without sufficiently explicit user consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.