Back to skill

Security audit

Writing Assistant

Security checks across malware telemetry and agentic risk

Overview

The available scan signals do not show malicious or suspicious behavior, but the actual skill artifact was not present for a full content review.

Install with normal caution, but review the actual skill files before granting file, network, account, credential, or spending permissions because the artifact content was not available in this adjudication workspace.

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.