OpenAI on Friday started rolling out Codex Safety, a synthetic intelligence (AI)-powered safety agent that is designed to seek out, validate, and suggest fixes for vulnerabilities.
The characteristic is out there in a analysis preview to ChatGPT Professional, Enterprise, Enterprise, and Edu prospects through the Codex net with free utilization for the subsequent month.
“It builds deep context about your venture to establish complicated vulnerabilities that different agentic instruments miss, surfacing higher-confidence findings with fixes that meaningfully enhance the safety of your system whereas sparing you from the noise of insignificant bugs,” the corporate stated.
Codex Safety represents an evolution of Aardvark, which OpenAI unveiled in personal beta in October 2025 as a manner for builders and safety groups to detect and repair safety vulnerabilities at scale.
During the last 30 days, Codex Safety has scanned greater than 1.2 million commits throughout exterior repositories over the course of the beta, figuring out 792 essential findings and 10,561 high-severity findings. These embrace vulnerabilities in varied open-source initiatives like OpenSSH, GnuTLS, GOGS, Thorium, libssh, PHP, and Chromium, amongst others. A few of them have been listed beneath –
- GnuPG – CVE-2026-24881, CVE-2026-24882
- GnuTLS – CVE-2025-32988, CVE-2025-32989
- GOGS – CVE-2025-64175, CVE-2026-25242
- Thorium – CVE-2025-35430, CVE-2025-35431, CVE-2025-35432, CVE-2025-35433, CVE-2025-35434, CVE-2025-35435, CVE-2025-35436
In keeping with the AI firm, the newest iteration of the applying safety agent leverages the reasoning capabilities of its frontier fashions and combines them with automated validation to attenuate the danger of false positives and ship actionable fixes.
OpenAI’s scans on the identical repositories over time have demonstrated growing precision and declining false optimistic charges, with the latter falling by greater than 50% throughout all repositories.
In an announcement shared with The Hacker Information, OpenAI stated Codex Safety is designed to enhance signal-to-noise by grounding vulnerability discovery in system context and validating findings earlier than surfacing them to customers.
Particularly, the agent works in three steps: it analyzes a repository to get a deal with on the venture’s security-relevant construction of the system and generates an editable menace mannequin that captures what it does and the place it is most uncovered.
As soon as the system context is constructed, Codex Safety makes use of it as a basis to establish vulnerabilities and classifies findings primarily based on their real-world influence. The flagged points are pressure-tested in a sandboxed atmosphere to validate them.
“When Codex Safety is configured with an atmosphere tailor-made to your venture, it may well validate potential points straight within the context of the operating system,” OpenAI stated. “That deeper validation can cut back false positives even additional and allow the creation of working proofs-of-concept, giving safety groups stronger proof and a clearer path to remediation.”
The ultimate stage entails the agent proposing fixes that greatest align with the system habits in order to cut back regressions and make them simpler to overview and deploy.
Information of Codex Safety comes weeks after Anthropic launched Claude Code Safety to assist customers scan a software program codebase for vulnerabilities and counsel patches.
