ClawHub
Back to skill

Security audit

git-platform

Security checks across malware telemetry and agentic risk

Overview

This skill is a Git forge command reference with broad activation triggers but no hidden execution or persistent behavior in the artifact.

Before installing, understand that this skill may appear during many git-related conversations and may suggest forge commands that mutate repository state. Treat create, close, merge, approve, comment, and API examples as commands to run only after you have confirmed the target repository, account, and intended action.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest includes broad, common triggers such as "git", "platform", "github", and "gitlab", which can cause the skill to activate in many ordinary developer conversations rather than only when explicitly needed. Over-broad activation increases the chance this skill influences unrelated workflows, injects forge-specific guidance unexpectedly, or crowds out more appropriate skills, which is a real security and reliability concern in agentic systems.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.