Back to skill

Security audit

📝 论文写作指导

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only multilingual translation skill with no executable code or hidden access, though its offline/privacy claim is not proven by the artifact.

Reasonable to install as a translation prompt. Do not treat the offline/privacy statement as proven, avoid pasting confidential documents unless you trust the runtime, and confirm the exact package slug before installing.

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

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.