ClawHub
Back to skill

Security audit

gitload

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward GitHub downloader skill, with ordinary file-writing and token-handling cautions but no hidden or malicious behavior in the artifact.

Use this skill only if you are comfortable invoking the external gitload-cli package. Prefer gh auth login for private repositories, avoid putting real tokens directly in commands, use fine-grained read-only tokens when needed, download into a fresh directory, and inspect downloaded code before running install or build commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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

Low
Confidence
81% confidence
Finding
The skill repeatedly instructs the user to download repository content into local directories and custom output paths, including the current directory, but it does not warn that existing files or directories may be created or overwritten. In a file-downloading skill, this omission can lead to accidental clobbering of local content or unsafe placement of untrusted files, especially when using '-o .' or similarly broad destinations.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The authentication examples show passing a GitHub personal access token directly on the command line using '--token ghp_xxxx' without warning that secrets in process arguments may be exposed via shell history, process listings, logs, or terminal recordings. Although intended for legitimate authentication, this is unsafe guidance and can lead to credential leakage.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.