CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HLiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI.
A critical vulnerability, dubbed AgentForger, in OpenAI's ChatGPT Workspace Agents allowed a single phishing link to deploy a rogue AI agent within a victim's organization. The vulnerability, discovered by Zenity Labs, e…
This week’s cybersecurity news highlights a significant Fortinet vulnerability dubbed ‘FortiBleed,’ where over 80,000 FortiGate devices have been compromised by suspected Russian-speaking threat actors. Simultaneously, t…
A critical vulnerability chain in LiteLLM, an open-source AI gateway, allows low-privilege users to escalate their permissions to full administrator and execute arbitrary code on the server. Researchers at Obsidian Secur…
