ClawHub
Back to skill

Security audit

build-family-law-practice-service-comparison-landing-page

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only marketing skill for drafting family law landing pages, with no executable code, install scripts, credential use, or hidden data access.

Before installing, treat outputs as marketing drafts only. Have a qualified human review claims, pricing cues, disclaimers, jurisdiction-specific advertising rules, and any content shown to clients; avoid entering confidential case details or client PII.

SkillSpector

By NVIDIA
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
88% confidence
Finding
The skill description and activation guidance are broad enough that an agent could invoke it in situations beyond pure marketing copy generation, including contexts where users may be seeking legal-information-adjacent content. In a legal domain, underspecified activation increases the chance of producing misleading or quasi-legal content without clear guardrails, review requirements, or exclusions.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The 'Use When' section lacks concrete trigger conditions, boundaries, and negative examples, so an agent may over-apply the skill whenever family-law-related content is requested. Because this skill operates in a regulated legal context, weak invocation constraints can cause unsafe routing to persuasive copy generation where factual accuracy, disclaimers, and jurisdictional compliance matter.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.