Back to skill

Security audit

looplink.app

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent Looplink integration, but it lets a live remote manifest define all callable tools and uses a permanent agent API key.

Install only if you trust Looplink to control the live MCP manifest and to protect a long-lived agent credential. Before linking an account, inspect the current manifest and avoid enabling write, delete, publish, share, or account-changing actions unless there is clear user confirmation and a way to revoke or rotate the apiKey.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.