ClawHub
Back to skill

Security audit

done

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises as an automatic installer, but it can replace installed skills and write outside the intended area if a ZIP package supplies an unsafe skill name.

Install only if you trust the ZIP files you will use with it and understand that it can replace existing OpenClaw skills. Inspect the archive's SKILL.md name first, keep backups of existing skills, and avoid using it on systems where the hard-coded Windows desktop path is not appropriate.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly describes reading ZIP archives and writing extracted content into both the WSL skills directory and a Windows desktop folder, yet no permissions are declared. That mismatch hides file system capabilities from users and reviewers, reducing informed consent and making the installer more dangerous because it performs cross-environment file writes and installs untrusted package contents.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README advertises automatic extraction, installation into WSL2, backup to the Windows desktop, and cleanup of temporary files without any warning, confirmation, scope limits, or explanation of what files and locations will be modified. This is dangerous because it normalizes silent filesystem and environment changes from a user-supplied archive, increasing the risk of unintended overwrites, unsafe installation of untrusted content, and destructive cleanup behavior.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation states that existing skills will be automatically overwritten, but it does not prominently warn that this can destroy or replace previously installed skill data. In this context, the skill is an installer that writes into trusted skill directories, so silent overwrite behavior increases the risk of accidental data loss or replacement of legitimate skills with malicious or tampered content.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The installer automatically deletes any existing skill directory in both WSL and Windows locations before copying the new contents, without confirmation, backup, or path safety validation on the derived skill name. Because the skill name comes from untrusted archive content, a crafted package could cause unintended overwrites or data loss in user directories, making the auto-install context materially more dangerous.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.