ClawHub
Back to skill

Security audit

code-reviewer

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward code-review skill that tells the agent to inspect code and produce a prioritized report, with no hidden execution or persistence behavior.

Install this when you want an agent to review code and produce a Markdown report. Use it only on projects you are comfortable letting the agent inspect, since effective security review can involve reading configuration files and spotting secrets.

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
87% confidence
Finding
The invocation description uses broad trigger phrases such as '代码审查', 'Code Review', and '代码优化', which can cause the skill to activate in overly broad situations. In an agent system, ambiguous routing can send unrelated or sensitive user content to this skill unexpectedly, increasing the chance of improper handling, confusion, or unsafe downstream behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.