ClawHub
Back to skill

Security audit

git-workflow-and-ver

Security checks across malware telemetry and agentic risk

Overview

This Git workflow skill is not malicious, but it requests command execution for repository-changing workflows and uses overly broad automatic activation language.

Review this skill before installing if you do not want broad Git automation. Use it only for explicit version-control tasks, and require confirmation before commit, branch, merge, tag, rollback, push, API-token use, or sending repository content to any external service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

High
Confidence
95% confidence
Finding
The activation text is extremely broad, saying to use the skill whenever efficiency, automation, batch processing, or workflow optimization is needed. That can cause the agent to invoke a repository-modifying skill in many unrelated contexts, increasing the chance of unintended git operations, inappropriate tool use, or exposure of sensitive code/content to the skill path.

Vague Triggers

High
Confidence
96% confidence
Finding
The trigger condition states the skill activates automatically whenever the user needs related operations, but it does not define precise boundaries for what qualifies. In a skill with exec capability and repository workflow scope, ambiguous triggering raises the risk of accidental autonomous execution of commands or repo changes without sufficiently explicit user authorization.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The description claims Chinese interaction support in a way that frames it as a default behavior without presenting a user choice. This can cause instruction mismatches, misunderstanding of confirmations or warnings, and reduced user awareness when the skill performs sensitive version-control actions.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The core feature text again specifies Chinese interaction without offering locale selection, which may override or conflict with the user's expected language. In an operational git workflow skill, that increases the risk that users misunderstand prompts related to commits, branching, merges, or rollback actions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.