ClawHub
Back to skill

Security audit

build-estate-planning-law-firm-service-comparison-landing-page

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown skill for drafting an estate-planning law firm landing page, with no executable code or hidden system access.

Before installing, treat this as a marketing drafting aid only. Provide jurisdiction, audience, approved services, pricing and claim constraints, and have a qualified human review the output before publishing or sending it to clients.

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
94% confidence
Finding
The description ends with an incomplete and overly broad trigger phrase ('Use when handling...'), which can cause the skill to be invoked in unintended legal-content scenarios. In a legal domain, ambiguous routing increases the chance of generating persuasive content without sufficient scoping, review, or safeguards, leading to misuse or inappropriate automation.

Vague Triggers

Low
Confidence
84% confidence
Finding
The suggested prompt is very broad and can trigger the skill without collecting necessary constraints such as jurisdiction, audience, service mix, compliance requirements, and whether output is marketing copy versus legal guidance. Because the skill operates in a legal-services context, underspecified prompts increase the risk of producing misleading claims or content that drifts toward unauthorized legal advice.

Static analysis

No suspicious patterns detected.