GPT-5.6 Sol Ultra Builds Full Chrome Exploit Chain Using 74 AI Subagents
ID: 90b725fa-f133-5567-baea-cfefd2905496
STIX ID: report--90b725fa-f133-5567-baea-cfefd2905496
Feed Name: Cyber Press
Threat Score
A report documents that OpenAI’s GPT-5.6 Sol Ultra autonomously developed a full exploit chain against Chrome (v149/V8 v14.9), progressing from a Maglev JIT type-confusion to native code execution by chaining primitives (addrof/fakeobj, large R/W primitives, address leaks, a WebAssembly compiler use-after-free) and demonstrating code execution (launching calc); the run used a hierarchical subagent architecture and scored highly on ExploitBench, raising concerns about AI-assisted weaponization of vulnerabilities.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.