All systems

OpenAI AI agent

OpenAI Aardvark / Codex Security

OpenAI's agentic security researcher and Codex Security workflow, now carrying direct credits across browsers, operating systems, network services, and media tooling.

12
Indexed entries
36
CVE IDs tracked
9
Critical/high entries
86%
Evidence index

What it is

Aardvark is OpenAI’s agentic security researcher. OpenAI describes it as an agent that reads repositories, identifies vulnerabilities, validates exploit paths in a sandbox, and attaches suggested fixes for human review. In 2026, the capability evolved into Codex Security.

What is verified

OpenAI’s public Aardvark announcement said ten responsibly disclosed vulnerabilities received CVEs. The March 2026 Codex Security preview lists 14 non-OpenSSL example CVEs. The ledger now also counts direct Codex-assisted credits in Apache HTTP Server, FFmpeg, Microsoft HTTP.sys, dnsmasq, FreeBSD, Chrome, Apple WebKit, and PostgreSQL. Chrome’s July and August releases add three direct credits; PostgreSQL’s August security release adds three more.

What is counted

The current ledger counts 36 unique CVEs across twelve grouped entries. Two OpenSSL examples in the Codex Security appendix remain outside this profile because the existing AISLE cluster needs a more precise shared-reporting map. OpenAI’s much larger private Daybreak totals remain context until public identifiers or accepted patches make individual findings auditable.

Chrome CVE-2026-9973 is not included in this profile because Chrome credits an OpenAI researcher without naming Codex Security. It remains in the Daybreak record with a qualified campaign-level attribution.

Source

Attributed findings

Catalogued entries credited to OpenAI Aardvark / Codex Security.

ID Title System Disclosed Severity
CVE-2026-15903, CVE-2026-17658, CVE-2026-76045 Chrome directly credits Codex Security on three new high-severity CVEs Out-of-bounds access and use-after-free in browser execution and graphics engines - direct OpenAI Aardvark / Codex Security (direct) Aug 18, 2026 high CVE-2026-14680, CVE-2026-16238 PostgreSQL directly credits Codex Security on two type-confusion RCEs Type confusion enabling arbitrary code execution as the database operating-system user - direct OpenAI Aardvark / Codex Security (direct) Aug 13, 2026 high CVE-2026-14669 Codex Security and V12 share credit on PostgreSQL to_char RCE Heap buffer overflow enabling database-server code execution - direct OpenAI Aardvark / Codex Security (direct) + V12 (self-reported) Aug 13, 2026 high CVE-2026-14431 Chrome directly credits Codex Security on V8 type-confusion CVE Type confusion - direct OpenAI Aardvark / Codex Security (direct) + OpenAI Daybreak (direct) Jun 30, 2026 high CVE-2026-49427, CVE-2026-49428 FreeBSD credits OpenAI Codex Security on two POSIX shared-memory CVEs Kernel memory corruption and local privilege escalation - direct OpenAI Aardvark / Codex Security (direct) Jun 30, 2026 high CVE-2026-43707, CVE-2026-43716, CVE-2026-43745 Apple credits Codex Security on three June 2026 WebKit CVEs Memory corruption, memory-handling crash, and out-of-bounds write - direct OpenAI Aardvark / Codex Security (direct) Jun 29, 2026 high CVE-2026-49975 Codex-assisted HTTP/2 Bomb reaches Apache and other major servers HTTP/2 denial of service through decompression work amplification - direct OpenAI Aardvark / Codex Security (direct) + OpenAI Daybreak (direct) Jun 22, 2026 medium CVE-2026-45250, CVE-2026-45251, CVE-2026-45253 Calif and Codex validate three FreeBSD local-privilege-escalation CVEs Use-after-free, credential confusion, and local privilege escalation - direct OpenAI Aardvark / Codex Security (direct) + OpenAI Daybreak (direct) Jun 22, 2026 high CVE-2026-4890 + 3 more Codex Security independently identifies four fixed dnsmasq CVEs DNS and DHCP parser memory-safety and denial-of-service flaws - direct OpenAI Aardvark / Codex Security (direct) + OpenAI Daybreak (direct) Jun 22, 2026 medium CVE-2026-49160 MSRC credits Codex collaboration for HTTP.sys denial of service HTTP/2 resource-consumption denial of service - direct OpenAI Aardvark / Codex Security (direct) Jun 9, 2026 high CVE-2026-6385 Calif.io credits OpenAI Codex on FFmpeg parser CVE Signed integer overflow and media-parser memory corruption - direct OpenAI Aardvark / Codex Security (direct) Jun 8, 2026 medium CVE-2025-32988 + 13 more OpenAI Codex Security publishes OSS CVE examples Open-source vulnerability discovery and validation cluster - direct OpenAI Aardvark / Codex Security (direct) Mar 6, 2026 high