Litellm
SSRF to the Model, Model to the Cloud: The Inference Layer Is 2026's Softest Attack Surface
Model gateways and inference servers are repeating two decades of solved web-security mistakes — default-open binds, pickle RCE, pre-auth SQLi, and SSRF straight into cloud credentials. A field guide to the AI control plane's softest links and how to harden them before the next 36-hour exploitation window.
BadHost (CVE-2026-48710): A Forged Host Header Walks Past Auth in Every Starlette App
BadHost (CVE-2026-48710) is a Host-header authentication bypass in Starlette before 1.0.1. One malformed header makes request.url.path lie to your middleware — unlocking protected routes on FastAPI, vLLM, LiteLLM, and MCP servers without credentials.
LiteLLM CVE-2026-42208: Pre-Auth SQLi in the AI Gateway, Exploited 36 Hours After Disclosure
A pre-authentication SQL injection in LiteLLM's auth path (CVSS 9.3) lets an unauthenticated attacker read and modify the proxy database — including upstream OpenAI and Anthropic API keys. First exploitation hit 36 hours after the advisory.
TeamPCP's Supply Chain Cascade: Trivy, KICS, LiteLLM, Telnyx Compromised — Now Pivoting to Ransomware via Vect
TeamPCP poisoned Trivy, KICS, LiteLLM, and Telnyx across GitHub Actions and PyPI in March 2026, harvested ~300 GB of CI/CD secrets, breached Cisco and AstraZeneca, and has now partnered with Vect RaaS to convert stolen credentials into ransomware deployments.