Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws
Summary
Researchers at Hacktron used Anthropic's Claude Opus 5 to chain two security flaws and gain access to OpenAI employees' accounts and an internal code repository: a memory corruption bug in the libheif image library (CVE-2026-32882, which scores 8.8 out of 10 for severity) that allowed remote code execution on OpenAI's public help forum, combined with a weakness in OpenAI's single sign-on (SSO, a shared login system) that let them take over staff accounts. The researchers responsibly reported their findings without reading source code or accessing customer data, and OpenAI confirmed a fix within 14 hours and paid a $6,500 bounty.
Solution / Mitigation
For self-hosted Discourse servers: rebuild on the latest image to get the patched libheif library, as a web-interface update alone may not replace the old library. The fixed self-hosted Discourse releases are 2026.7.0, 2026.6.1, 2026.5.2, and 2026.1.6. The underlying libheif flaw was fixed in libheif version 1.22.0 in May 2026. Sites hosted by Discourse were already patched automatically.
Classification
Affected Vendors
Related Issues
CVE-2026-63086: text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compat
CVE-2026-34371: LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the e
Original source: https://thehackernews.com/2026/09/claude-opus-5-helped-researchers-take.html
First tracked: September 19, 2026 at 08:01 AM
Classified by LLM (prompt v3) · confidence: 92%