How to use Codex Privacy Hud: what you can do with it

3 use cases

• See what a Codex session discloses, live

  Install the HUD and read confirmed points, recipients and denials for each Codex session.

  • REPO inin-zou/codex-privacy-hud
  • Codex
  • Security and science
  • Intermediate
  View prompt

  Using the repo inin-zou/codex-privacy-hud, install the plugin on this macOS machine and open the Privacy HUD for the session <session-id>. Report confirmed points, distinct disclosures, confirmed recipients, denials issued and whether a percentage is shown. Verify the session began from a genuine SessionStart before treating its accounting as evidence-based.

  Share Email me this

• Repair the HUD runtime after a plugin update

  Check runtime alignment with doctor, then run the printed repair command in another terminal.

  • REPO inin-zou/codex-privacy-hud
  • Codex
  • Security and science
  • Advanced
  View prompt

  In the repo inin-zou/codex-privacy-hud, set PRIVACY_HUD_BUNDLE to <bundle-path> and PRIVACY_HUD_DATA to <data-path>, then run the doctor command. Expected output: a report of runtime alignment, and if it is misaligned, the exact repair command. Verify that you do not run the repair command yourself unless the user has approved the downloads it may perform.

  Share Email me this

• Block network commands that name sensitive paths

  Use the default-on lexical network guard to deny Codex network commands that reference sensitive files.

  • REPO inin-zou/codex-privacy-hud
  • Codex
  • Security and science
  • Intermediate
  View prompt

  Using the repo inin-zou/codex-privacy-hud, install the plugin and run a test network command that references <sensitive-path-placeholder> inside a Codex session. Expected output: a denial from the lexical network guard and a denials-issued count in the HUD. Verify that no file contents were opened or rewritten by the guard, as the README states.

  Share Email me this

Quick start with Codex Privacy Hud

1. Check you have what it needs: macOS on Apple Silicon or Intel (Linux and Windows are not packaged); Codex CLI installed and signed in, with `codex --version` printing a version; Python 3.11 or newer on your PATH.
2. Open inin-zou/codex-privacy-hud on GitHub and read the README and license.
3. Run codex --version and confirm it prints a version such as codex-cli 0.154.0.
4. Run python3 --version and confirm Python is 3.11 or newer.
5. Run curl -fsSL https://raw.githubusercontent.com/inin-zou/codex-privacy-hud/main/install.sh | sh to install the plugin.
6. Start a new Codex session and open the Privacy HUD readings for it.

These steps come from our top use case, See what a Codex session discloses, live, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for inin-zou/codex-privacy-hud

claude mcp add --transport http deduped https://dedupedai.com/mcp

Codex Privacy Hud alternatives · Best AI repos for Security and science

About this repo

• Who it is forDevelopers and security-minded teams on macOS who run Codex CLI and want a local record of what their agent discloses.
• Why it is hot109 stars, launched 51 days ago
• LanguagePython
• Sourcegithub.com/inin-zou/codex-privacy-hud · Back to Hot repos

Requirements

• macOS on Apple Silicon or Intel (Linux and Windows are not packaged)
• Codex CLI installed and signed in, with `codex --version` printing a version
• Python 3.11 or newer on your PATH
• About 3 GB of disk if you want name and address detection

Related repos

• Trended earlier REPO Ch1nfo/RiftX RiftX RiftX is a local TypeScript workbench that combines AI agent chat, a Playwright browser, multi-agent task coordination, and evidence capture for explicitly authorized web security testing.
• Trended earlier REPO Elite588/Hacker Hacker Elite588/Hacker is a curated collection of cybersecurity references, scripts, tools, labs, and training material, maintained by Omar Santos as supplemental material for his books, courses, and live training.
• Trended earlier REPO Mah3Sec/ForgeGuardian Forge Guardian ForgeGuardian is a local-first, Go-based software supply chain security scanner that checks project dependencies across 9 ecosystems with 8 scan engines.