ClawHub
Back to skill

Security audit

Workforce Planning Framework

Security checks for vulnerabilities and agentic risk

Overview

This is a static workforce-planning guide; it handles sensitive HR topics but does not include executable code, hidden access, persistence, or data transfer behavior.

Install only for users authorized to handle workforce planning data. Treat any employee-level compensation, performance, engagement, flight-risk, or diversity information as confidential, minimize fields where aggregated data is enough, and involve HR/legal review before using outputs for employment decisions.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs users to collect and process sensitive employee data including skills ratings, flight risk, compensation, tenure, utilization, and diversity-related information, but provides no privacy, minimization, access-control, retention, or legal-compliance guidance. In a workforce planning context this is materially risky because these data points can enable profiling, unfair employment decisions, insider misuse, and regulatory violations if handled improperly.

Static analysis

No suspicious patterns detected.