All systems

OpenAI AI agent

OpenAI Aardvark / Codex Security

OpenAI's agentic security researcher, now surfaced as Codex Security with public OSS CVE examples.

1
Indexed entries
14
CVE IDs tracked
1
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 the system had been applied to open-source projects and that ten responsibly disclosed vulnerabilities received CVE identifiers. OpenAI’s March 2026 Codex Security research-preview post says 14 CVEs had been assigned and lists example CVE IDs.

What is counted

The current ledger counts the 14 non-OpenSSL example CVE IDs from OpenAI’s Codex Security appendix. Two OpenSSL examples in that appendix are not counted under this profile because they overlap with the AISLE OpenSSL cluster and need dual-reporting context.

Source

Attributed findings

Catalogued entries credited to OpenAI Aardvark / Codex Security.