ClawHub
Back to skill

Security audit

git提交前审查

Security checks across malware telemetry and agentic risk

Overview

This is a coherent pre-commit review skill that inspects local git changes and has no evidence of hidden persistence, credential use, repository mutation, or exfiltration.

Install this if you want a lightweight git-diff review helper. When invoking it, specify the repository or files you want reviewed, and avoid including changed files that contain secrets unless you intend the agent to inspect them.

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
92% confidence
Finding
The trigger phrases include very broad everyday expressions such as '检查一下改动' and '看看能不能提交', which can match normal conversational requests and cause the skill to activate unexpectedly. In an agent setting, over-broad activation can lead to unintended repository inspection, execution of git commands, and disclosure of file names or code diffs beyond what the user explicitly scoped.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.