Amazon Ecs

Security checks across malware telemetry and agentic risk

Overview

This looks like a real Amazon ECS integration, but it can let an agent make broad changes to AWS container resources without clear safety limits.

Install only if you are comfortable letting an agent operate AWS ECS through Membrane. Use a least-privilege AWS role, preferably against non-production resources first; restrict account, region, clusters, and services; and require explicit approval before create, update, delete, deployment, task stop/start, or scaling actions. Review how to revoke the Membrane connection before use.

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 explicitly documents a generic proxy mechanism for direct API requests and highlights support for mutating methods like POST, PUT, PATCH, and DELETE without any guardrails, confirmation requirements, or warnings about destructive effects. In an agent setting, this lowers the barrier to executing high-impact changes to ECS resources, increasing the risk of accidental or overly broad modifications when the model cannot fully assess operational consequences.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal