ClawHub
Back to skill

Security audit

People & Culture Playbook

Security checks for vulnerabilities and agentic risk

Overview

This is a plain HR playbook skill with broad people-ops advice, but it does not include code, credential access, persistence, or hidden behavior.

This skill is suitable as a general people-ops planning aid. Users should treat its outputs as advisory and involve qualified HR, legal, or compliance reviewers for jurisdiction-specific employment decisions, investigations, terminations, accommodations, pay decisions, or other regulated employee matters.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s trigger scope is broad enough to activate on a wide range of HR, coaching, org design, and workforce planning requests, which can cause the agent to inappropriately route sensitive or regulated people-ops tasks through this skill. In HR contexts, overbroad triggering increases the risk of the model giving authoritative-seeming guidance on hiring, performance, compensation, DEI, or compliance-adjacent matters without sufficient context, jurisdiction checks, or human review.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.