Ngrok

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Ngrok API helper, with the main caution that it can make user-directed changes or deletions to Ngrok resources.

Install only if you want the agent to use your Ngrok API access. Use the least-privileged token available, and require explicit confirmation before creating, updating, or deleting tunnels, domains, or endpoint configuration.

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: 84% confidence
Finding: The skill explicitly documents a generic request primitive supporting POST, PUT, PATCH, and DELETE without requiring confirmation or warning about state-changing and irreversible operations. In an agent context, this increases the risk of unintended destructive API calls against Ngrok resources such as tunnels, reserved domains, or endpoint configurations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal