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.
Calif says researcher Quang Luong directed OpenAI's Codex to audit the HotSpot JVM and found a heap out-of-bounds write in the x86-64 AVX-512 Base64 decode intrinsic in about an hour, with a first working exploit two hours later, for under $200 in tokens (company claims). It affects OpenJDK 17.0.6 and later on CPUs with AVX-512 VBMI; Calif reports pre-auth RCE in its own tests against Keycloak, Jira, Confluence, Artifactory, Jenkins and PingFederate. Red Hat rates it Critical; VulnCheck says denial of service is trivial but RCE needs non-trivial heap grooming, and that it was not known to be exploited in the wild on Nov 17. Oracle shipped fixes the same day.
Depi's researchers fed a crafted issue into the OpenAI Codex issue-labeling workflow in OpenAI's GitHub repository, made the agent run commands, escaped its sandbox and recovered runner tokens; they describe a path to publishing a malicious @openai/codex npm package that they did not carry out. SecurityWeek reports OpenAI fixed it and paid an initial $1,000 bounty.
Conductor's app runs several coding agents such as Claude Code and Codex in parallel. Terms undisclosed; its cloud service shuts Nov 20, when cloud user data deletion begins, and a new product is planned for early 2027.
Sources: InfoWorld, “Meta acquires Conductor as AI coding shifts toward multi-agent development”
Check Point named a new attack class, "prompt adware", after a Chinese-language Codex jailbreak bundle that plants persistent ads in Codex's identity file.
- OpenAI to acquire Pierre Computer Company
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)
OpenAI's Codex Security researchers found a Brotli decoder flaw enabling unauthenticated remote code execution in Node.js, Bun and Envoy.
Sources: Envoy advisory GHSA-3wvj-j6qm-62mr, “Out-of-Bounds Write in Brotli Decompressor”; The Register, “Microsoft releases emergency .NET security fixes for Google Brotli bug”
- Pwn2Own Ireland: AI tools exploited
Codex and LiteLLM fall on day one ($40,000 each); final results include Nvidia Dynamo.
Sources: Cybersecurity News; SecurityWeek, “Google Pixel 10 Exploits Earned Hackers $560,000 at Pwn2Own”
- 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
- OpenAI releases GPT-6.1 Sol
API, Codex and Work model, distinct from the GPT-6 Sol ChatGPT tier and GPT-5.6 Sol.
Sources: OpenAI
- OpenAI releases GPT-6 Astra
New flagship model; later powers OpenAI Dots and the Codex "Ultrafast" tier.
Sources: OpenAI
- AI agents mass-exploit PaperCut zero-days, compromising 440 servers (PaperCut AI agent campaign)
A likely Russian-speaking actor used AI to build and test exploits for PaperCut NG/MF flaws CVE-2026-81578 and CVE-2026-82078 (disclosed Aug 27), then ran hundreds of agents on OpenAI's Codex harness with a DeepSeek model against at least 440 instances at 395 organizations in 48 countries, per GreyNoise. It went from an empty workspace to first remote code execution in under four hours and reached domain admin at 12 organizations.
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)
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
- OpenAI release notes, Sep 2026 [link needed]
- Cybersecurity News [link needed]
- ZDI schedule [link needed]
- Depi, “Backdooring the next release of Codex through GitHub Action pipeline exploit chaining”, Nov 11 2026