ClawHub

Darwinbox

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Darwinbox HR integration, but it gives an agent broad ability to change sensitive HR records without clear confirmation safeguards.

Install only if you trust Membrane and are authorized to connect Darwinbox. Use a least-privilege or test Darwinbox account where possible, and require the agent to show the exact record, endpoint, HTTP method, fields, and expected effect before any employee, candidate, leave, attendance, or raw proxy write.

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 (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises destructive HR operations such as rejecting candidates or updating leave status without any guidance to verify user intent, confirm risky changes, or distinguish read-only from write actions. In an agent setting, this increases the chance of unauthorized or mistaken modifications to sensitive personnel records and workflow state.

Missing User Warnings

High
Confidence
95% confidence
Finding
The proxy section enables arbitrary authenticated requests, including POST, PUT, PATCH, and DELETE, but does not warn that these can directly modify or delete live Darwinbox HR data. Because the skill targets an HRMS containing sensitive employee and recruitment information, omission of approval and scope controls materially raises the risk of damaging or unauthorized changes.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal