ClawHub
Back to skill

Security audit

Git Workflow Cn Tool Free

Security checks across malware telemetry and agentic risk

Overview

This is a Git workflow helper whose command guidance is mostly expected for its purpose, but users should be careful around destructive Git cleanup and deletion examples.

Install only if you want an agent to help with Git command workflows. Review state-changing commands before allowing execution, especially branch deletion, stash clearing, reset, commit amend, push, and clean operations; use previews or backups for cleanup commands and avoid applying the broad project-management trigger outside Git tasks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger condition is overly broad and includes generic project-management and collaboration requests that are not tightly scoped to Git operations. In an agent environment with exec capability, this can cause the skill to be invoked unexpectedly and steer the assistant into running Git-related commands in contexts where the user did not explicitly request repository modification.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill documents destructive branch-deletion commands, including forced deletion, without a consolidated warning about irreversible data loss or the conditions under which recovery may fail. In a tool-using agent, surfacing these commands as normal guidance increases the chance that users or the agent apply them unsafely, causing loss of unmerged work.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
This section includes commands that permanently delete stash entries and remove untracked files/directories, but it does not clearly warn that these actions may be irreversible. Because the skill is classified as MD+EXEC and intended to drive agent command execution, omission of strong safeguards materially raises the risk of accidental data destruction on the user's workspace.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.