https://losec.io/blog Deep technical write-ups, exploit chains and research methodology from the LoSec AI security research lab. en Fri, 17 Jul 2026 00:00:00 GMT https://losec.io/blog/no-keys-required-inside-the-attack-surface-of-xllm https://losec.io/blog/no-keys-required-inside-the-attack-surface-of-xllm Fri, 17 Jul 2026 00:00:00 GMT @hypnguyen1209 xLLM is a cutting-edge language model with a unique attack surface. This post explores the potential vulnerabilities and security considerations when interacting with xLLM. xllm security ai https://losec.io/blog/the-night-i-decided-to-kill-frida https://losec.io/blog/the-night-i-decided-to-kill-frida Fri, 17 Jul 2026 00:00:00 GMT @hibana Frida is a dynamic instrumentation toolkit for developers, reverse-engineers, and security researchers. This post chronicles the night I decided to stop using Frida and the reasons behind it. frida hooking cafe https://losec.io/blog/the-final-days-of-huntr-oss https://losec.io/blog/the-final-days-of-huntr-oss Thu, 16 Jul 2026 00:00:00 GMT @khanhdlq Before Huntr shut down its traditional open-source bug bounty program and shifted toward Huntr 2.0, I returned to the platform one last time, discovered three vulnerabilities in NLTK in less than twelve hours alongside GPT-5.5 Ultra, and ultimately received $1,625 in bounties. huntr disclosure ai