Onelogin

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate OneLogin integration, but it gives an agent broad authenticated control over a sensitive identity system without clear write-action safeguards.

Review before installing. Use a dedicated least-privileged OneLogin connection, prefer Membrane's discovered actions over raw proxy calls, and require explicit human approval before any POST, PUT, PATCH, or DELETE request that could affect users, groups, apps, roles, sessions, policies, or authentication settings.

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: 88% confidence
Finding: The skill explicitly documents use of a generic proxy request mechanism that supports destructive HTTP methods like POST, PUT, PATCH, and DELETE without requiring confirmation or warning about operational impact. In an identity-management context, this could lead an agent to modify users, apps, policies, or authentication settings directly, increasing the risk of unintended security or availability changes.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal