Zeet

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Zeet integration, but it gives an agent broad authenticated control over cloud resources without enough built-in scoping or confirmation guidance.

Install only if you are comfortable letting an agent use your Membrane/Zeet account. Use a least-privileged account or tenant, confirm the exact connection, project, environment, action, and endpoint before changes, and require explicit approval for deploy, create, update, or delete operations.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description is broad enough that an agent could invoke it for vague requests about Zeet data or workflows without sufficient user confirmation or task scoping. In an agentic system, overly broad routing can cause unintended external actions, data access, or workflow execution if the harness auto-selects skills from metadata alone.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal