---
title: "After spending billions, OpenAI still has gaps in its cybersecurity"
type: signal
url: https://frontiernewswire.com/s/after-spending-billions-openai-still-has-gaps-in-its-cybersecurity-ecf67c5f
published: 2026-09-21T16:24:03.000Z
byline: "Source: CSO Online"
---

# After spending billions, OpenAI still has gaps in its cybersecurity

Source: CSO Online · Published 2026-09-21 · Canonical: https://frontiernewswire.com/s/after-spending-billions-openai-still-has-gaps-in-its-cybersecurity-ecf67c5f

Two separate reports of security flaws in OpenAI systems highlight how even a company spending billions on developing its own AI-powered cybersecurity testing tools remains vulnerable. In one incident, researchers breached OpenAI systems with the help of a rival AI developer’s tools, while another group of researchers tricked OpenAI’s Codex agent into bypassing its sandbox controls. Researchers from Hacktron chained multiple vulnerabilities to achieve remote code execution and gain access to OpenAI employee accounts and internal systems, according to a blog post detailing their findings. “On July 25, 2026, we chained two critical vulnerabilities to compromise multiple OpenAI employees’ ChatGPT accounts,” Hacktron researchers Harsh Jaiswal, Mohan Pedhapati and Rahul Maini wrote . “With these accounts, we could then access internal OpenAI repositories, and potentially many other connectors.” They said the attack began with a flaw in an image processing library that enabled remote code ex

In this story: [Hacktron](https://frontiernewswire.com/companies/hacktron)

## Sources

- [Read the original at CSO Online](https://www.csoonline.com/article/4224453/after-spending-billions-openai-still-has-gaps-in-its-cybersecurity.html)

## Related on Frontier

- [CPython flaw exposes AI inference servers to sandbox escape attacks](https://frontiernewswire.com/s/cpython-flaw-exposes-ai-inference-servers-to-sandbox-escape-attacks-8807cb51)
- [Binance heist is stark example of AI governance gaps and basic security failures](https://frontiernewswire.com/s/binance-heist-is-stark-example-of-ai-governance-gaps-and-basic-a6e3881a)
- [OpenAI’s GPT-6 Cyber ups the ante on vulnerability discovery](https://frontiernewswire.com/s/openais-gpt-6-cyber-ups-the-ante-on-vulnerability-discovery-0de731e7)
- [Partnering with Hacktron to find vulnerabilities in OpenAI’s systems](https://frontiernewswire.com/s/partnering-with-hacktron-to-find-vulnerabilities-in-openais-systems-4dbbcc41)
- [OpenAI built an AI pipeline to find, exploit and patch Linux flaws](https://frontiernewswire.com/s/openai-built-an-ai-pipeline-to-find-exploit-and-patch-linux-flaws-0c04d1b8)

---

[More Latest Signal](https://frontiernewswire.com/) · [Signals](https://frontiernewswire.com/verified-reporting)