ClawHub
Back to skill

Security audit

Code Review Zh

Security checks across malware telemetry and agentic risk

Overview

This is a simple Chinese code-review skill that only asks to read code and provide review feedback.

Install this if you want a Chinese-language code review assistant. It may read code or repository files you ask it to review, so avoid invoking it on private or unrelated files unless you intend those files to be included in the review.

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 skill advertises very broad trigger phrases such as general code review and problem-finding requests, which can overlap with routine user prompts and cause the skill to activate more often than intended. Over-broad activation increases the chance of context hijacking, accidental routing, or invocation in situations where a narrower, explicitly requested review workflow would be safer.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.