Hivebrite

Security checks across malware telemetry and agentic risk

Overview

The skill is a legitimate Hivebrite integration, but it gives an agent broad authenticated power to change live Hivebrite data without clear confirmation safeguards.

Install only if you are comfortable giving an agent delegated Hivebrite access through Membrane. Use the least-privileged Hivebrite account available, prefer read-only discovery first, and manually confirm any create, update, delete, billing, role, SSO, GDPR, notification, or configuration action before it runs.

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 running arbitrary actions and direct proxy requests, including mutating HTTP methods like POST, PUT, PATCH, and DELETE, without requiring confirmation or warning that these can alter or remove remote Hivebrite data. In an agent setting, this increases the risk of unintended destructive or high-impact changes being executed against a live tenant.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal