ClawHub
Back to skill

Security audit

moreninha

Security checks for vulnerabilities and agentic risk

Overview

This is a focused literature-reference skill that reads bundled public-domain text and does not request system access or lasting changes.

Installers should treat the bundled HTML as source material only, not as something to execute in a browser. The skill is appropriate for literary help on A Moreninha and carries only the normal risk of relying on a bundled text edition for citations and interpretation.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (9)

Hidden Instructions

High
Category
Prompt Injection
Content
<!DOCTYPE html>
<html lang="es">
<!-- .52 -->
Confidence
60% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High
Category
Prompt Injection
Content
<!DOCTYPE html>
<html lang="es">
<!-- .52 -->
<head profile="http://a9.com/-/spec/opensearch/1.1/">

    <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High
Category
Prompt Injection
Content
<h2 class="sr-only">Opciones de navegación</h2>
					<div id="opciones">
					<ul class="nav navbar-nav" role="menubar">
<!--                      <li class="navbar-toggle btn-lg boton-buscar" data-toggle="collapse" data-target="#buscador"><span class="glyphicon glyphicon-search"></span><span class="sr-only">Buscar</span></li>-->
												<li role="menuitem" class="dropdown">
						<a href="#" class="dropdown-toggle" title="Portales relacionados" data-placement="bottom" data-toggle="dropdown" role="button" aria-expanded="false"><span class="glyphicon glyphicon-link"><span>Portales</span></span> <span class="caret"></span></a>                        
				        <ul class="dropdown-menu" role="menu">
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High
Category
Prompt Injection
Content
<li role="menuitem"><a class="verficha" href="/obra/a-moreninha--0/" data-toggle="tooltip" title="Ver ficha" data-placement="bottom"><span class="glyphicon glyphicon-credit-card"><span>Ficha</span></span></a></li>				  					  			  
					  </ul>					  
					  </div>                      
					 <!-- <div id="encabezado_2">
					 					<h2 class="tituloBloque">A moreninha</h2>					
					</div>		-->		
				</div>
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High
Category
Prompt Injection
Content
<div class="modal-content" id="modal-nota-div">
							<div class="modal-header">
								<button type="button" class="close" data-dismiss="modal" aria-label="Close"><span aria-hidden="true">&times;</span></button>
								<!-- Para quitar la nota doble<h4 class="modal-title">Nota</h4>-->
							</div>
							<div id="modal-nota-contenido" class="modal-body">
								<p>One fine body&hellip;</p>
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Whitespace Padding

Medium
Category
Prompt Injection
Content
<script>
            (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
            (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
Confidence
70% confidence
Finding
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The instruction 'Responda em pt-BR por padrão' imposes a default locale in the skill behavior. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; this file does not provide either.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The file contains Spanish interface/instruction text such as "Saltar al contenido principal", "Buscador Buscar", and "Selecciona una palabra y presiona la tecla d para obtener su definición" embedded directly in the content. This imposes a specific language on the user with no indication of locale choice or justification.

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
The document declares `lang="es"` at the top level, which fixes the page language to Spanish. Under the policy rule, forcing a specific language without opt-in can be a natural-language locale-policy issue when no user choice or justification is provided in the file.

Static analysis

No suspicious patterns detected.