website-cloner 网站1:1本地复刻

• Outcome: Review
• Latest audit: Jun 18, 2026 at 8:04 AM UTC
• Version:
  1.0.0

Overview

This skill is a website-cloning guide whose local download behavior is mostly coherent, but it under-scopes authorization and includes attribution-replacement guidance that could enable deceptive reuse.

Install only if you intend to clone sites you own or have permission to copy. Before using it, add your own guardrails: confirm authorization, preserve attribution unless you own the content, avoid private/internal URLs, avoid unlicensed substitute assets, and review any npx-installed browser tooling before execution.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Context-Inappropriate Capability

High

• Confidence: 98% confidence
• Finding: The skill explicitly instructs replacing original author attribution and profile links with the user's own, which goes beyond technical local mirroring and facilitates misrepresentation or plagiarism. In the context of cloning third-party websites, this materially increases the likelihood that the cloned site will be redistributed as if it were created by the user.

Context-Inappropriate Capability

Medium

• Confidence: 88% confidence
• Finding: The skill advises sourcing missing images from elsewhere when they cannot be downloaded directly, which expands the activity from local mirroring into content substitution without provenance control. This can enable copyright infringement, deceptive reconstruction, or insertion of unauthorized assets while presenting the result as a faithful clone.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill provides end-to-end instructions for cloning and modifying arbitrary third-party websites without any warning about authorization, copyright, trademark, or terms-of-service constraints. In this context, omission of such guardrails makes misuse substantially easier and normalizes potentially unlawful copying and redistribution.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The skill instructs the agent to send requests to arbitrary user-supplied URLs using curl and related tooling without warning that this discloses network metadata and may interact with sensitive or internal endpoints. In an agent setting, this can be abused for unintended outbound requests, privacy leakage, or access to non-public resources.

VirusTotal

VirusTotal findings are pending for this skill version.