ClawHub
Back to skill

Security audit

Landing Page Conversion Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused conversion-audit checklist with no hidden execution, persistence, or data access beyond user-provided pages and funnel context.

Before installing, be aware that this skill may be invoked for broad landing-page review phrasing and it may ask for business metrics, ad examples, and funnel data. Only provide URLs and performance data you are comfortable sharing with your agent, and review any optional external Docker-based funnel-builder recommendation before running it.

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
91% confidence
Finding
The manifest description says to use the skill when asked to "review, critique or improve" a landing page, sales page, opt-in page, product page or checkout flow. Terms like "review" and "improve" are broad, everyday requests, and the description does not clearly bound when this skill should not activate beyond a later markdown section that may not be used for routing.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The example trigger "Review my landing page" is a generic request that could refer to design, copy, UX, or general feedback rather than a conversion-focused audit. Without explicit constraints in the trigger example itself, it risks accidental invocation for routine page-review requests.

Static analysis

No suspicious patterns detected.