Back to skill

Security audit

Nexus Corporate Onboarder

Security checks for vulnerabilities and agentic risk

Overview

The skill is not overtly malicious, but it asks agents to work with HRIS and employee training data without enough privacy and control guidance.

Review before installing in any real workplace environment. Only use it with explicit authorization, least-privilege access, minimized or anonymized employee data, and legal/privacy review for compliance modules or HRIS-connected workflows.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description is broad and does not define clear activation boundaries, approved use cases, or disallowed tasks. In a corporate onboarding and HR context, this increases the chance the agent will be invoked for sensitive employee-data processing or compliance-related decisions outside its intended scope, leading to overreach and unsafe handling of regulated information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises HRIS integration and training analytics involving employee onboarding, completion, and engagement metrics, but it provides no warning or safeguards for handling HR-related or personal employee data. This is dangerous because users may supply sensitive PII, performance data, or compliance records without guidance on minimization, consent, retention, access control, or legal review, increasing privacy, insider-risk, and regulatory exposure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.