Fireeye

Security checks across malware telemetry and agentic risk

Overview

This FireEye integration is coherent, but it gives an agent broad authenticated access to a sensitive security system without clear guardrails for write or delete actions.

Install only if you trust Membrane and are comfortable granting it FireEye access. Use a least-privilege FireEye account, prefer predefined Membrane actions, and require explicit confirmation before any POST, PUT, PATCH, DELETE, task execution, or other workflow-changing request.

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: 92% confidence
Finding: The skill explicitly documents a generic proxy request capability with support for POST, PUT, PATCH, and DELETE, but it does not require user confirmation or warn about potentially destructive effects. In an agent setting, this increases the risk that the model could issue unsafe state-changing requests against the connected FireEye environment based on ambiguous or manipulated prompts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal