ClawHub
Back to skill

Security audit

Git Cli Tool Free

Security checks across malware telemetry and agentic risk

Overview

This Git helper is mostly coherent, but it gives an agent broad Git mutation authority with an overly broad trigger and limited confirmation guidance.

Install only if you want an agent to help run Git commands in your repositories. Before using it, require the agent to show status/diff first and ask before staging all files, committing, amending, deleting branches, rebasing, pushing, changing global Git credential settings, or creating SSH keys.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger condition is overly broad: it says to use the skill for code generation, programming assistance, debugging/testing, and deployment-related tasks, even though the skill is specifically for Git CLI operations. In an agentic environment with exec access, this can cause the skill to activate in unrelated workflows and run Git commands that modify repository state or interact with remotes without sufficiently specific user intent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill includes commands that can change local repository state and remote history, including staging, committing, branch operations, pull/rebase, push, and force-with-lease, but it does not consistently require explicit warnings or confirmations before executing them. In a tool-enabled agent, that creates a meaningful risk of unintended commits, branch changes, rebases, or remote updates triggered from ambiguous user requests.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.