Firehydrant

Security checks across malware telemetry and agentic risk

Overview

This FireHydrant skill is coherent, but it gives an agent broad authenticated power to change or delete incident-management data through a raw API proxy without clear confirmation guidance.

Install only if you are comfortable letting the agent operate against FireHydrant through Membrane. Use a least-privileged FireHydrant account, prefer predefined Membrane actions, pin the CLI version where possible, and require explicit confirmation before any request that creates, updates, or deletes incident data.

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: 91% confidence
Finding: The skill documents a generic proxy request mechanism that supports all HTTP methods, including POST, PUT, PATCH, and DELETE, but does not warn that these can modify or delete production incident-management data. In an agent setting, presenting raw request capability without confirmation or guardrails increases the risk of unintended destructive actions against FireHydrant resources.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal