Realchinese

• Outcome: Pass
• Latest audit: Jun 6, 2026 at 10:14 AM UTC
• Version:
  1.1.2

Overview

This is a local Chinese text detection and rewriting skill whose executable code matches its stated purpose and does not show hidden network, credential, persistence, or destructive behavior.

Before installing, treat it like any executable skill: review the small Python scripts, run it in a normal low-privilege environment, and only provide text you are comfortable processing locally. I found no evidence that it sends data out, installs dependencies, persists, or accesses credentials.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly instructs users to run local Python commands and import package modules, but provides no warning that this executes arbitrary local code from the skill package. In a skill ecosystem where content may be untrusted, encouraging immediate execution increases the chance that a user runs malicious or unsafe code without reviewing it first.

VirusTotal

65/65 vendors flagged this skill as clean.