Back to skill

Security audit

Static Site Cloner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward static website recreation helper with no hidden execution, persistence, or credential access, though users should only use it on sites they are authorized to reproduce.

Use this only for websites you own, have permission to inspect, or are using for clearly lawful learning. Do not use it to imitate brands, login pages, checkout flows, private/internal pages, or copyrighted content verbatim.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (7)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · assets/template.html (reported line 284)May include surrounding context.

html
</head>

<body>
  <!-- Navigation Bar -->
  <header class="navbar">
    <div class="navbar__inner container">
      <a href="#" class="navbar__logo">Logo</a>

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow instructs the agent to fetch and analyze arbitrary target URLs without any guardrails about authorization, privacy, robots/terms compliance, or handling of sensitive pages. That makes it easier to scrape or reconstruct third-party sites in ways that may violate site policies or expose private/internal content if a protected or sensitive URL is supplied.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad enough to activate on requests to 'clone,' 'copy,' or 'recreate' third-party websites, which can facilitate copyright infringement, brand impersonation, or phishing-style page replication. In the context of a skill explicitly designed to reproduce site structure and visuals from a URL, this increases the likelihood of misuse rather than merely supporting benign educational front-end work.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document declares lang="en", which imposes a specific language/locale in natural-language metadata. Under the policy, locale constraints should either be user-selectable or clearly justified as region-specific; this file provides neither.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The example markup explicitly sets the document language to English in a markdown file. Under the policy rule, forcing a specific language/locale without opt-in or documented justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This example likewise fixes the page language to English with no indication that the locale is optional or region-specific. That can conflict with a policy requiring language choice or opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file uses Chinese as the sole language from the title onward and does not indicate that language selection is optional or user-driven. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.