codexdesktop-rebuild-electron

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to clone a project repository from GitHub (https://github.com/Haleclipse/CodexDesktop-Rebuild.git) and install development dependencies using the Node Package Manager (NPM).
  • [COMMAND_EXECUTION]: The documentation includes commands for building and running the application, such as electron-forge start, electron-forge make, and cross-platform builds using Docker. It also provides a pattern for Inter-Process Communication (IPC) that allows the renderer process to trigger shell command execution in the main process.
  • [DYNAMIC_EXECUTION]: The skill outlines the use of Vite for dynamic development serving and the use of @electron/rebuild to compile native Node.js modules for the Electron environment.
  • [INDIRECT_PROMPT_INJECTION]: The application architecture involves taking user-provided text from a webview and executing it as a command, creating an attack surface where untrusted data could influence system commands.
  • Ingestion points: Input is gathered from a textarea element in the renderer process (described in src/webview/main.js).
  • Boundary markers: The provided code snippets do not specify any delimiters or boundary markers to separate instructions from data.
  • Capability inventory: The skill documentation includes scripts for file system modification (patch-copyright.js) and IPC handlers for shell command execution (execute-codex-command).
  • Sanitization: The provided examples do not demonstrate sanitization or validation of the input before it is passed to the command execution logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 03:57 AM