frontend-ui-clone
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads external assets such as images, CSS, and fonts from user-specified target URLs to create self-contained clone files. This behavior is essential to the skill's primary function and targets the site requested by the user.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to verify the availability of local dependencies like Playwright and Firecrawl, and to scaffold new projects using
npx create-next-app. These operations represent standard functionality for a developer-oriented cloning tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites, creating a surface for potential indirect prompt injection. 1. Ingestion points: External web content is retrieved from a user-provided target URL using Playwright, Firecrawl, or WebFetch (SKILL.md). 2. Boundary markers: There are no explicit delimiters or instructions for the agent to ignore embedded instructions in the fetched content. 3. Capability inventory: The skill possesses capabilities for file system writes, shell command execution via Bash, and network requests via WebFetch (SKILL.md). 4. Sanitization: The skill mitigates risks by stripping
<script>tags from the extracted HTML body content during assembly to prevent the execution of original site scripts in the cloned output.
Audit Metadata