Humi

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Humi integration, but it deserves careful review because it can give an agent broad authenticated access to sensitive HR data and raw write/delete API operations.

Install only if you are comfortable letting an agent operate through a Humi-connected Membrane account. Use the least-privileged Humi account available, prefer prebuilt Membrane actions over raw proxy requests, require explicit approval for any create/update/delete action, verify the CLI package before global installation, and revoke the Membrane/Humi connection when finished.

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: 94% confidence
Finding: The skill explicitly documents a generic proxy mechanism for arbitrary Humi API requests and lists mutating methods like POST, PUT, PATCH, and DELETE without requiring confirmation or warning about destructive side effects. In an HR context, this can enable accidental or overly permissive modification of sensitive employee, payroll, or policy data if an agent uses raw requests instead of constrained actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal