skills/rheinmir/setup/web-clone/Gen Agent Trust Hub

web-clone

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (harness/scripts/web-clone.py) and install global Node.js packages (npm i -g single-file-cli) to facilitate website cloning.
  • [EXTERNAL_DOWNLOADS]: The skill references external tools and templates from third-party GitHub repositories, including gildas-lormeau/SingleFile and JCodesMore/ai-website-cloner-template, which are used during the snapshotting and reconstruction phases.
  • [PROMPT_INJECTION]: The skill's 'reconstruct' mode processes untrusted data from external websites to reverse-engineer components and logic. This represents an indirect prompt injection surface where malicious instructions on a target website could attempt to influence the agent's analysis or the resulting code generation.
  • [COMMAND_EXECUTION]: The reconstruction pipeline involves the execution of generated scripts for asset downloading and running build commands (npm run build) on code derived from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 06:25 AM
Security Audit — agent-trust-hub — web-clone