ClawHub
Back to skill

Security audit

Git工具包专业版

Security checks across malware telemetry and agentic risk

Overview

The skill is a Git automation guide, but it includes unsafe credential-storage instructions and destructive branch-cleanup commands without enough safeguards.

Review before installing. Use this only in repositories where branch deletion, hook changes, aliases, and remote configuration changes are intended. Do not use the shown plaintext credential helper or token-in-URL pattern; prefer SSH, an OS-backed credential manager, or a scoped secret mechanism, and require confirmation before any cleanup command deletes branches.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation includes branch-deletion commands that can remove local branches in bulk without an explicit warning, dry-run step, or confirmation requirement. In an agent context with exec/write capabilities, users may copy or automate these commands and unintentionally destroy work or lose recoverable branch state.

Missing User Warnings

High
Confidence
99% confidence
Finding
The skill recommends storing credentials with 'credential.helper store' and embedding a token directly in the remote URL. This is dangerous because tokens may be written to plaintext storage, shell history, process listings, config files, logs, or accidentally committed/shared, leading to repository compromise and broader supply-chain exposure.

Ssd 3

Medium
Confidence
99% confidence
Finding
The plain-language guidance normalizes directly storing and embedding repository credentials in Git configuration and remote URLs. In the context of a Git automation skill with exec/read/write tools, this materially increases the chance of credential leakage through config inspection, logs, screenshots, process arguments, copied commands, and repository metadata, enabling unauthorized access or malicious code pushes.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.