文本对比工具

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward text and file comparison skill with no evident hidden, network, credential, persistence, or destructive behavior.

Installers should be aware that generic words like diff or compare may invoke the skill unexpectedly. Use it for text or files you intend to compare, since diff output can reveal the contents of those inputs in the chat.

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
94% confidence
Finding
The activation phrases are broad enough to match common conversational terms such as '对比', 'diff', and '找不同', which can cause unintended skill invocation during normal user interactions. In an agent setting, accidental activation can route unrelated content into file/text comparison workflows, increasing the chance of data exposure or confusing behavior even though the skill itself is not overtly dangerous.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal