ClawHub
Back to skill

Security audit

Educational Content & How-To

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed educational-content planning guide with no executable code, persistence, or hidden data handling.

Before installing, confirm you want this skill to use brand and audience context for educational marketing content. Treat downstream publishing through WoopSocial as something that should remain under explicit user review, especially for regulated or sensitive topics.

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
Confidence
83% confidence
Finding
The eval examples use very broad requests like "Help me make an educational post" and "Make us some how-to content" without explicit boundaries for when this skill should activate versus adjacent skills. In an agentic routing system, this can cause over-triggering, misrouting, or inappropriate handling of requests, especially where other skills govern formatting, publishing, or sensitive-topic safeguards.

Static analysis

No suspicious patterns detected.