FortiGate Hardening

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed external API helper for generating FortiGate hardening configurations, with no executable code or automatic firewall changes.

Install only if you trust the API provider. Use pseudonymous session IDs, omit userId when possible, and avoid sending secrets, firewall credentials, internal IP ranges, or confidential architecture details. Review any generated FortiGate configuration against your FortiOS version, current CIS guidance, and your normal change-control process before deployment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documentation explicitly instructs clients to send both a sessionId and a userId, but provides no privacy notice, retention guidance, minimization rationale, or handling restrictions. This creates a real privacy and security concern because operators may pass stable identifiers to a third-party service without understanding how they are stored, correlated, or exposed in logs and generated artifacts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal