ClawHub
Back to skill

Security audit

Worktrunk

Security checks across malware telemetry and agentic risk

Overview

This appears to be a worktree-management skill with disclosed destructive cleanup commands, so it is usable with caution rather than unsafe by default.

Before using merge or remove commands from this skill, check `git status`, confirm there is no uncommitted or local-only work you need, and use any keep/dry-run-style option where available. Treat branch deletion and worktree removal as irreversible local cleanup operations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill documents `vx wt merge` as performing a squash merge plus deletion of the worktree and branch, but it provides no explicit warning, confirmation guidance, or recovery caveat. In an AI-agent workflow context, users may copy commands verbatim or let agents invoke them automatically, increasing the chance of unintended local data loss or branch deletion.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The removal commands are documented without warning that they delete local worktree directories and, with `--with-branch`, can also delete branches. Because this skill is intended for parallel AI-agent use, an agent or user following the examples could irreversibly remove local state or work-in-progress without appreciating the destructive effect.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.