Back to skill

Security audit

Entangle

Security checks across malware telemetry and agentic risk

Overview

No concrete malicious or review-worthy behavior was supported by the supplied scan evidence.

Install only after reviewing the actual skill text and any requested permissions, because this adjudication had clean scanner inputs but limited accessible artifact evidence.

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

65/65 vendors flagged this skill as clean.

View on VirusTotal