Frontegg

Security checks across malware telemetry and agentic risk

Overview

This skill appears aimed at managing a Frontegg tenant, but it exposes broad live-tenant action and raw request capability without enough guardrails for high-impact changes.

Install only if you trust the publisher and intend to let an agent operate inside your Frontegg tenant. Use the least-privileged credentials available, prefer read-only discovery first, and require explicit approval for any create, update, delete, SSO, SCIM, billing, permissions, or security-policy request, especially through a raw proxy.

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: 87% confidence
Finding: The skill documents action execution and raw proxy requests against a live Frontegg tenant without clearly warning that these operations can change authentication, user, billing, SSO, SCIM, and security-policy state. In an agent context, this increases the chance that an AI will perform destructive or configuration-altering calls without adequate user confirmation or safety checks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal