职业教育课材一体化开发

Security checks across malware telemetry and agentic risk

Overview

This is a vocational education content skill with a small language helper, and the reviewed artifacts do not show hidden access, credential use, persistence, network calls, or unsafe automation.

Install if you want a Chinese-first vocational education course-material design aid. Be aware it may choose Chinese or English based on local language environment variables; set an explicit language preference if that matters.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
72% confidence
Finding
Automatically detecting the user's language environment without explicit choice can create unnecessary privacy and transparency concerns, especially if the detection relies on client context, locale, or other environmental signals. In this educational skill, the impact is limited, but it still normalizes behavior based on inferred user attributes rather than informed consent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal