ClawHub

Namely

Security checks across malware telemetry and agentic risk

Overview

This Namely HR integration is coherent, but it can read and change sensitive employee and business data without clear approval safeguards.

Review before installing. Use a least-privileged Namely account, understand what Membrane can access, and require explicit human confirmation before any create, update, delete, employee profile, payroll-related, or raw proxy request.

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 (3)

Vague Triggers

Medium
Confidence
80% confidence
Finding
The invocation description is very broad and could cause the agent to select this skill for generic Namely-related requests without enough task scoping. In an HRIS context, overbroad routing is more dangerous because the connected system exposes sensitive employee and payroll-adjacent data as well as write actions, increasing the chance of unintended reads or modifications.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill lists destructive actions like deleting announcements without any confirmation, authorization, or rollback guidance. In a business HR platform, that can lead to accidental or unauthorized changes to organizational communications and records if the agent executes actions too eagerly.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
Profile create/update actions affect employee data, but the skill provides no warning about data integrity, privacy, or approval requirements. Because Namely contains sensitive HR information, an agent could inadvertently alter employee records, compensation-related metadata, or personal details without sufficient scrutiny.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal