ClawHub
Back to skill

Security audit

Git Workflows Tool Free

Security checks across malware telemetry and agentic risk

Overview

This Git helper is mostly coherent, but it presents destructive Git commands without enough warnings or confirmation steps.

Review this skill carefully before installing. It is not malicious based on the inspected artifact, but users should only run its destructive Git examples after checking `git status`, creating a backup branch or stash, confirming whether commits were pushed, and verifying that any worktree being removed has no needed changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (6)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger condition is overly broad, stating the skill should be used whenever AI model calling, agent orchestration, or LLM applications are involved. In an agent environment, this can cause the skill to activate outside its intended Git-advanced-help context, increasing the chance that destructive Git guidance or commands are suggested inappropriately.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This section includes history-rewriting and potentially work-dropping commands such as interactive rebase, abort/continue flows, and commit manipulation without a prominent safety warning before execution. In a tool-using agent, users may follow these steps directly and unintentionally rewrite shared history or lose uncommitted work.

Missing User Warnings

High
Confidence
99% confidence
Finding
The skill recommends `git reset --hard` as a recovery step without clearly warning that it permanently discards uncommitted changes in the working tree and index. In this skill context, the command is especially dangerous because it is presented as a normal remediation workflow, making accidental data loss more likely.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The force-removal worktree command is presented without warning that it can delete a worktree containing uncommitted or unpushed changes. In a command-driven agent workflow, this omission can lead to accidental loss of in-progress work when users treat the snippet as routine cleanup.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
git reflog --date=relative

# 恢复到指定状态
git reset --hard HEAD@{2}      # 回到 2 步之前的状态
git reset --hard ghi789        # 回到指定提交

# 恢复误删的分支
Confidence
98% confidence
Finding
git reset --hard

Tool Parameter Abuse

High
Category
Tool Misuse
Content
# 恢复到指定状态
git reset --hard HEAD@{2}      # 回到 2 步之前的状态
git reset --hard ghi789        # 回到指定提交

# 恢复误删的分支
git branch recovered-branch abc123
Confidence
98% confidence
Finding
git reset --hard

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.