Public story · 2026-03-11 · source-backed
Codex Security Scans 1.2M Commits — 10,561 High-Severity Issues
Story
OpenAI launched Codex Security in research preview — an AI security agent that builds project context, generates editable threat models, identifies vulnerabilities, and validates findings in sandboxes. In 30 days: 792 critical and 10,561 high-severity issues found, false positive rates dropped 50%+. Free for Pro/Enterprise users for the first month. OpenAI
Related stories
Each link below shares sources, entities, or timing with this story.
Shared entities / Same source domain / Shared topic / What happened next
OpenAI Codex Security: 1.2M Commits Scanned, 10,561 High-Severity Vulnerabilities Found — 50% False Positive Reduction
Both cover Codex Security, Enterprise, High, OpenAI; reported by the same outlet (openai.com); overlapping topics (agent, codex, commit, context, false).
Shared entities / Same source domain / Shared topic / Earlier coverage / Tension
AI Security Arms Race: Codex Security vs Anthropic-Mozilla (22 CVEs)
Both cover Codex Security, OpenAI; reported by the same outlet (openai.com); overlapping topics (agent, codex, found, high-severity, security).
Shared entities / Same source domain / Shared topic / What happened next
Codex CLI v0.130 Ships Remote Control, Computer Use, and a Browser Extension
Both cover Free, OpenAI; reported by the same outlet (openai.com); overlapping topics (agent, codex, context).
Shared entities / Shared topic / What happened next
Scan every AI-generated PR with a dedicated security scanner before merge.
Both cover Codex Security, OpenAI; overlapping topics (codex, commit, false, found, security); picks up the Codex Security thread on 2026-03-29.
Shared entities / Same source domain / Shared topic / Earlier coverage
OpenAI Acquires Promptfoo + Codex Security Hits 14 CVEs — Agent Security Goes Platform
Both cover Codex Security, Enterprise; reported by the same outlet (openai.com); overlapping topics (agent, codex, security).
Shared entity: OpenAI / Same source domain / Shared topic / Earlier coverage / Tension
GPT-5.4 Launches with Native Computer Use and 1M Context.
Both cover OpenAI; reported by the same outlet (openai.com); overlapping topics (codex, context, false).
OpenAI Frontier: Enterprise Agent Platform Directly Competes With Incumbents
Both cover OpenAI; reported by the same outlet (openai.com); overlapping topics (agent, context, enterprise).
Shared entity: OpenAI / Same source / Shared topic / Earlier coverage
Skills You Should Learn This Week
Both cover OpenAI; cite the same source (OpenAI); overlapping topics (agent, security).
Source trail
Entities
Provenance
- Canonical issue
- Ramsay Research Agent — 2026-03-11
- AI generated
- no
- Story unit
- 2026-03-11-codex-security-scans-1-2m-commits-10-561-high-severity-issues
- Labels
- source-backed, canonical briefing excerpt