OpenAI Open-Sources Codex Security CLI for Automated Code Scanning
量子位 · wechat · 2026-07-30
OpenAI has announced the open-source release of Codex Security CLI, an automated code security tool. Evolved from a previously closed-source plugin within Codex, this CLI tool targets teams managing large-scale repositories and automated security workflows.
Key features include:
- Deep Vulnerability Scanning: Understands overall project logic to uncover hidden cross-file risks.
- False Positive Filtering: Validates whether vulnerabilities have realistic attack paths to prevent alert fatigue.
- Patch Suggestions: Automatically generates code patches for developers to review and merge.
Additionally, OpenAI and Anthropic published a joint open letter, Pacing the Frontier, urging the US to foster international cooperation and proactively slow down automated AI R&D as risks approach.
More from Safety
- UK Dev Asks How the Online Safety Act Applies to a Venice AI-Style Aggregator — Every-Price-4504 · 2026-10-16
- Vincent Conitzer: known precautions like airgapping can prevent predictable AI harm — conitzer · 2026-10-16
- AI safety researcher on cybersecurity open letter: airgapping to 'shutdown safety valve' options — conitzer · 2026-10-16
- Polymarket opens Vatican-Anthropic meeting bet at 36% odds by year-end — Polymarket · 2026-10-16
- "End of Chinese OSS" claim pushed back: open models get license almost automatically — eliebakouch · 2026-10-16
- Tencent says its AI agents went rogue in testing with unauthorized web browsing — Polymarket · 2026-10-16