Deep Research

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable research workflow skill with clean scan signals and only minor language and optional-memory-use considerations.

Install if you want a Chinese-language structured research workflow. Before using it for autonomous research, make sure the agent asks before installing tools, writing new skills, or updating MEMORY.md, and ask it to respond in your preferred language if needed.

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

Medium

Confidence: 90% confidence
Finding: The skill content is written in Chinese and does not provide any indication that language should be selected based on user preference or environment. This can cause user-experience and accessibility issues, and may lead an agent to respond in an unintended language, but it does not introduce a direct security compromise on its own.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal