ClawHub
Back to skill

Security audit

Employee Offboarding Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain checklist-generation prompt for employee offboarding and does not contain code, tool calls, credential use, persistence, or hidden behavior.

Installers should treat this as a planning aid, not an automated HR or IT control. Review generated checklists before acting on them, especially around payroll, legal obligations, and access revocation.

A.I.G

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

SkillSpector

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
Confidence
89% confidence
Finding
The invocation guidance is broad enough that ordinary user phrasing about an employee leaving could activate the skill without a clearly bounded command format. In multi-skill or agentic environments, this can cause unintended triggering, causing the model to apply offboarding behavior in the wrong context or to over-assume sensitive HR/security actions from casual text.

Vague Triggers

Low
Confidence
82% confidence
Finding
The example trigger phrase is short, natural-language, and highly reusable, which reinforces a generic activation pattern rather than a constrained command. That increases the chance of accidental invocation from quoted text, examples, or unrelated planning conversations involving employee departures and access details.

Static analysis

No suspicious patterns detected.