Autonomous research agents identify remote code execution vulnerabilities at a 50% rate, nearly double the 26% seen across the broader CVE ecosystem, according to a GTIG report published September 30,…
Internet measurement has identified 39,155 assets presenting the LiteLLM AI gateway fingerprint, with deployments concentrated in the United States (9,792), China (2,629), Japan (2,030), India (1,855)…
Wiz Research found that a one-character Bearer token ("Bearer a") bypassed authentication in LiteLLM's Model Context Protocol gateway, tracked as CVE-2026-59822, after 90 days of honeypots mimicking A…
A critical authentication bypass in LiteLLM's MCP Streamable HTTP endpoint, tracked as CVE-2026-59822, allowed unauthenticated callers to list and invoke gateway-configured MCP tools by sending a forg…
Microsoft Security Research has documented attacks targeting AI infrastructure components, including LiteLLM, RAGFlow, and Kestra, which were compromised and abused for credential theft, persistence, …
On May 8, 2026, BerriAI disclosed CVE-2026-42271, a command-injection flaw in LiteLLM, one of the most widely deployed open-source AI gateways. The vulnerability scored CVSS 8.8 and affects releases f…