Truework

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Truework integration, but it gives agents broad authenticated access to sensitive employment data with limited guardrails around raw API calls and changes.

Install only if you are comfortable connecting a Membrane-managed Truework account. Use a least-privileged account where possible, prefer discovered Membrane actions over raw proxy calls, and require explicit user approval before creating, updating, patching, deleting, or retrieving highly sensitive employment records.

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 (1)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The skill description is overly broad: 'Manage data, records, and automate workflows' could cause an agent to invoke this Truework skill for generic data-management tasks unrelated to employment verification. In a security-sensitive domain handling employment and income records, over-broad routing increases the chance of unnecessary access to sensitive data or use of the wrong integration.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal