Join Nostr
2026-10-27 16:48:20 UTC

Cyber Security News (RSS Feed) on Nostr: Researchers Exploit OpenAI API Flaw to Extract Hidden GPT-5.6 Reasoning Traces ...

Researchers Exploit OpenAI API Flaw to Extract Hidden GPT-5.6 Reasoning Traces

Researchers at Xint found an OpenAI API flaw that exposed hidden reasoning in GPT-5.6 models by routing prompts through a conversation-compaction feature. The method, called compaction smuggling, bypassed protections introduced in August 2026. According to Xint, OpenAI confirmed the bug, deployed an undisclosed fix on October 23, and awarded the team a $6,000 bounty. The […]

The post https://cybersecuritynews.com/researchers-exploit-openai-api-flaw/ appeared first on https://cybersecuritynews.com.

https://cybersecuritynews.com/researchers-exploit-openai-api-flaw/