ClawHub
Back to skill

Security audit

Leadership

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown leadership-coaching skill with no code or hidden system access, though users should be careful with sensitive employee information.

Installers should understand this as a coaching and planning aid, not an HR system of record. Avoid entering unnecessary sensitive employee details, confidential personnel matters, or information your organization requires to stay in approved HR tools.

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
96% confidence
Finding
The description says the skill is for 'leaders at every level' and covers broad situations like difficult conversations, decisions under pressure, and ambiguity, but it does not define any specific trigger phrases, invocation boundaries, or exclusions. This creates a risk of unintended invocation because the activation scope overlaps with common workplace discussion topics.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly says it tracks development conversations and commitments, which implies collecting and retaining potentially sensitive employee performance data without any privacy, retention, consent, or access-control guidance. In a leadership/people-management context, that data can include performance concerns, interpersonal issues, or career plans, creating confidentiality and misuse risks if stored or surfaced improperly.

Static analysis

No suspicious patterns detected.