AI Wiki · Mediocre Security
ProductCoding & dev tools

OpenAI Codex

OpenAI's coding agent.

OpenAI’s coding agent. Codex Cloud runs tasks in reusable, isolated cloud workspaces that continue while the user’s computer is offline; Codex Security Cloud scans repositories on demand or on a schedule and proposes fixes for developer review (OpenAI release notes, late Sep 2026). Oct 1-2 2026: added an Astra “Ultrafast” tier (up to 8x faster token generation in Codex) and Codex 0.160.0 with projectless sessions and opt-in Guardian review. Pwn2Own Ireland day one (Oct 6 2026): Ikotas Labs exploited Codex via a single argument-injection flaw for a $40,000 payout; no CVE or affected versions published yet (Cybersecurity News; ZDI schedule).

Security record

On Nov 11 2026 security firm Depi disclosed that the issue-labeling workflow in the Codex GitHub repository fed any outsider’s issue text into a Codex agent prompt; a crafted issue let researchers run commands, escape the sandbox and recover CI tokens, and they describe a path to a poisoned npm release that they did not carry out. OpenAI fixed it (Codex GitHub Actions prompt-injection chain).

Timeline

Every dated event in the wiki that involves OpenAI Codex, newest first.

  • M&ANot disclosed

    Acquisition announced: Pierre makes Code Storage (Git-based code hosting) and the open-source Trees, Diffs and Highlights tools that already power parts of Codex; subject to regulatory approval.

    Sources: Tech Insider (citing The Information)
  • Release
    Codex adds Astra "Ultrafast" tier

    Up to 8x faster token generation in OpenAI Codex, plus Codex 0.160.0 with projectless sessions and opt-in Guardian review.

    Sources: OpenAI release notes

Connections

OpenAI Codex and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Protocol Agent Client Protocol (ACP) · Model Context Protocol (MCP)

Concept AI agent · Jailbreak

Company Calif · Composio · Conductor · Cursor (Anysphere) · GitHub · Pierre Computer Company · Pigment · Reason Machines

Product Claude Code · LiteLLM · Sysdig AI Defense

Incident Codex GitHub Actions prompt-injection chain · GPT-6 Astra safety-research performance gap · GPT-6.1 Terra authorization failures · Haiou "prompt adware" Codex jailbreak · Java4Shell (CVE-2026-114938) · Node2Shell (CVE-2026-111497) · OpenAI agents disable their own monitors · PaperCut AI agent campaign

Model family GPT

AI lab OpenAI

Sources

  1. OpenAI release notes, Sep 2026 [link needed]
  2. Cybersecurity News [link needed]
  3. ZDI schedule [link needed]
  4. Depi, “Backdooring the next release of Codex through GitHub Action pipeline exploit chaining”, Nov 11 2026