Back to skill

Security audit

HR

Security checks for vulnerabilities and agentic risk

Overview

This is a plain HR guidance skill with some broad and sensitive advice areas, but it does not install code, request credentials, run commands, or add persistence.

Before installing, treat this as general HR support rather than legal advice. For termination, discrimination, wage-and-hour, privacy, or jurisdiction-specific matters, use qualified HR or employment counsel review before acting.

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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill’s trigger scope is unusually broad, covering nearly any workplace question involving people, management, or employment. This can cause the skill to activate in contexts where specialized HR/legal guidance is inappropriate or where a narrower domain skill should respond, increasing the chance of overcollection of sensitive personnel details or unsafe quasi-legal advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The termination section gives concrete operational steps such as access revocation, reference handling, and scripted firing guidance, but does not place a prominent safety boundary immediately around those actions. In an HR skill, that can lead users to treat the content as universally safe procedure despite jurisdictional legal differences, privacy obligations, and risks of wrongful termination, retaliation, or mishandled account disablement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.