LiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint
78Vexday Risk Score
Patch now. It exploitation observed by VulnCheck and has a working public exploit.
ssvc Actcvss 8.7epss 4.0%
from disclosure to weapon43 days
Published on NVDApr 6
1st PoC+43d
VulnCheckApr 6
exploitation probability
4.0%top 10% of all CVEs
observed exploitation
yesVulnCheck
2 public exploit(s)
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.0, the /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to modify proxy configuration and environment variables, register custom pass-through endpoint handlers pointing to attacker-controlled Python code, achieving remote code execution, read arbitrary server files by setting UI_LOGO_PATH and fetching via /get_image, and take over other privileged accounts by overwriting UI_USERNAME and UI_PASSWORD environment variables. Fixed in v1.83.0.
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:L/SI:L/SA:N
Affected products
BerriAI · litellmpublic PoCs found — 2
githubgithub.com/learner202649/CVE-2026-35029-PoC★ 0vulncheckvulncheck.com/xdb/bd8d4646a8f2unverified⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.
References
https://access.redhat.com/errata/RHSA-2026:13545https://access.redhat.com/errata/RHSA-2026:28960https://access.redhat.com/errata/RHSA-2026:30056https://access.redhat.com/security/cve/CVE-2026-35029https://bugzilla.redhat.com/show_bug.cgi?id=2455474http://seclists.org/fulldisclosure/2026/Apr/17https://github.com/BerriAI/litellm/security/advisories/GHSA-53mr-6c8q-9789https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-35029.json