NewsSANS ISC Diary
Scans for LiteLLM/Starlette (CVE-2026-42271, CVE-2026-48710), (Mon, Nov 16th)
Linked advisories
- CVE-2026-48710Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.4.5 security update
- CVE-2026-48710Red Hat Security Advisory: Red Hat AI Inference Server 3.3.5 (CUDA)
- CVE-2026-48710Red Hat Security Advisory: RHOAI 2.25.12 - Red Hat OpenShift AI
- CVE-2026-48710Red Hat Security Advisory: Red Hat AI Inference Server 3.3.5 (ROCm)
- CVE-2026-48710Red Hat Security Advisory: RHOAI 3.4.4 - Red Hat OpenShift AI
- CVE-2026-48710Red Hat Security Advisory: RHOAI 3.3.5 - Red Hat OpenShift AI
- CVE-2026-48710Red Hat Security Advisory: satellite/foreman-mcp-server-rhel9 container image available as a Technology Preview
- CVE-2026-48710Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (cpu)
- CVE-2026-48710Red Hat Security Advisory: satellite/iop-vulnerability-engine-rhel9 container image available as a Technology Preview
- CVE-2026-48710Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (spyre)
- CVE-2026-42271LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to pre…
- CVE-2026-48710Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (cuda)
- CVE-2026-48710Kludex Starlette: HTTP Request Smuggling
- CVE-2026-48710Starlette is a lightweight ASGI framework/toolkit. Prior to version 1.0.1, the HTTP `Host` request header was not validated before being used to reconstruct …
- CVE-2026-48710Red Hat Security Advisory: satellite/iop-advisor-engine-rhel9 container image available as a Technology Preview
- CVE-2026-42271LiteLLM: Authenticated command execution via MCP stdio test endpoints
- CVE-2026-48710Red Hat Security Advisory: Migration Toolkit for Applications
- CVE-2026-48710Red Hat Security Advisory: satellite/iop-vulnerability-engine-rhel9 container image available as a Technology Preview
- CVE-2026-42271LiteLLM: Mehrere Schwachstellen
- CVE-2026-48710Debian starlette: security update
- CVE-2026-42271LiteLLM: Authenticated command execution via MCP stdio test endpoints
- CVE-2026-48710Kludex Starlette — Kludex Starlette HTTP Request/Response Smuggling Vulnerability
- CVE-2026-48710Red Hat Security Advisory: RHOAI 3.3.7 - Red Hat OpenShift AI
- CVE-2026-48710Starlette has missing Host header validation that poisons request.url.path, bypassing path-based security checks
- CVE-2026-48710Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (cpu)
- CVE-2026-48710Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (cuda)
- CVE-2026-48710Red Hat Security Advisory: RHOAI 3.4.2 - Red Hat OpenShift AI
- CVE-2026-48710BadHost: Missing Host header validation poisons request.url.path, bypassing path-based security checks
- CVE-2026-42271BerriAI LiteLLM: BerriAI LiteLLM Command Injection Vulnerability
- CVE-2026-48710Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.4.5 security update
- CVE-2026-42271BerriAI LiteLLM — BerriAI LiteLLM Command Injection Vulnerability
- CVE-2026-48710Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.6 Container Release Update
- CVE-2026-48710Red Hat Security Advisory: RHOAI 3.4.5 - Red Hat OpenShift AI
- CVE-2026-48710Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (spyre)
- CVE-2026-42271BerriAI LiteLLM: Betriebssystem-Befehlsinjektion
Affected vendors and products
- BerriAI BerriAI LiteLLM
- Debian Starlette
- Encode Encode Starlette
- Kludex Starlette
- LiteLLM LiteLLM
- Open Source Litellm
- Red Hat Red Hat AI Inference Server
- Red Hat Red Hat Ansible Automation Platform 2
- Red Hat Enterprise Linux AI
- Red Hat Migration Toolkit For Applications
- Red Hat Red Hat OpenShift AI (RHOAI)
- Red Hat Redhat Openshift Lightspeed
More on LiteLLM
Other advisories
- CriticalCVE-2026-40217LiteLLM: Schwachstelle ermöglicht Ausführen von beliebigem Programmcode mit Administratorrechten
- CriticalCVE-2026-42208LiteLLM: Mehrere Schwachstellen
- Mediumbsi:WID-SEC-2026-4522LiteLLM: Schwachstelle ermöglicht Offenlegung von Informationen
- Highghsa:GHSA-g5ff-637f-6q2mLiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`
- Not ratedosv:GHSA-g5ff-637f-6q2mLiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`
- Not ratedosv:GHSA-hhww-mrg2-969hLiteLLM vulnerable to reflected XSS in /sso/debug/callback
- Mediumghsa:GHSA-hhww-mrg2-969hLiteLLM vulnerable to reflected XSS in /sso/debug/callback
- CriticalCVE-2026-114612LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key
Other news entries
- Angriffe auf Lücken in Apache Axis und Roller, LiteLLM, Synology und mehrNewsheise Security
- CISA Warns of 4 Exploited Flaws Linked to Ransomware, Cryptomining, and LLMjacking AttacksNewsThe Hacker News
- Amazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API KeysNewsThe Hacker News
- LiteLLM: Schwachstelle ermöglicht Offenlegung von InformationenVulnerabilityBSI CERT-Bund
- Lessons from cybersecurity Black WeekNewsESET WeLiveSecurity
- LiteLLM supply chain attack started with an exposed master keyNewsThe Register — Security
- Leaked LiteLLM Master Key Let Attackers Steal GitHub Tokens and Hijack Release PipelineNewsThe Hacker News
- LiteLLM: Schwachstelle ermöglicht Privilegieneskalation und CodeausführungVulnerabilityBSI CERT-Bund
Source: https://isc.sans.edu/diary/rss/33522
ID