LowVulnerabilityLLM-specific
CVE-2026-59819: LiteLLM file read through /health/test_connection endpoint
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-59819
- Published
- Record updated
- Affected
- litellm < 1.83.10
- Fixed in
- 1.83.10
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.6%
Summary
LiteLLM, an AI Gateway proxy that exposes LLM APIs in OpenAI or native format, contains a flaw tracked as CVE-2026-59819. Before 1.83.10-stable, the /health/test_connection endpoint resolved request-supplied environment and OIDC file references in litellm_params. A proxy administrator or another privileged caller allowed to test model connections could read local files through an oidc/file/ reference.
Mitigation
Fixed in 1.83.10-stable.
Affected packages in the Exposure Registry
Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.
- litellmPyPILLM dependency since 2023-07-27 · 54 tracked dependents
Related items
- MediumWhen LLM Gateways Go Wrong: Findings from LiteLLMSimilar attack · Check Point Research
- HighCVE-2026-109403: conductor-oss conductor server-side request forgery in agent card fetchingSimilar attack · NVD/CVE Database
- InfoExploring Backdoor Vulnerabilities and Fairness Challenges in Generative Models: A SurveySimilar attack · ACM Digital Library (TOPS, DTRAP, CSUR)
- LowSmall AI Models Could Soon Self-Replicate on IoT Devices, Anthropic WarnsSimilar attack · SecurityWeek
- MediumCVE-2026-108940: Mistral.rs path traversal through calibration_apply save_cimatrix argumentSimilar attack · NVD/CVE Database