Meta's Llama Framework Flaw Exposes AI Systems to Remote Code Execution Risks

A high-severity security flaw has been disclosed in Meta's Llama large language model LLM framework that, if successfully exploited, could allow an attacker to execute arbitrary code on the llama-stack inference server. The vulnerability, tracked as CVE-2024-50050, has been assigned a CVSS score ...

CVE-2024-50050

creationtimestamp| type| source ---|---|--- 2024-10-23 17:23:17+00:00| seen| https://t.me/cvedetector/8690 2025-01-23 13:54:32+00:00| seen| https://bsky.app/profile/r-netsec.bsky.social/post/3lgfztkse6w2c 2025-01-23 15:45:06+00:00| published-proof-of-concept| https://t.me/thebugbountyhunter/9561...