Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🛡️
Not in CISA KEV
CRITICAL severity

CVE-2026-114612 — BerriAI

CRITICALFix: BerriAI/litellm@1d5fdc8

CVE-2026-114612 is a critical-severity (CVSS 9.9) Improper Privilege Management vulnerability. No vendor fix is recorded yet; mitigation options are listed below.

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic…

Published
Updated
Affected
—
Patched
See advisory
Exploits
None indexed
Exploitation data as of Oct 26, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

EPSS Exploitation Probability

via FIRST.org ↗
0.3%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs25th percentile — riskier than 25% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

CVE-2026-114612 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.

Where this sits among everything scored

Of 396,257 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.

Description

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted metadata containing a forged administrator credential encrypted and returned by the API-key flow. Replaying that ciphertext as a bearer token causes the proxy to trust the forged proxy administrator identity, permitting administrative access and arbitrary commands through the MCP stdio endpoint. Versions 1.87.0 through 1.90.x require EXPERIMENTAL_UI_LOGIN to be enabled, while versions after 1.91.0 are exploitable in the default configuration. This issue was fixed in LiteLLM 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2.

Detection & mitigation playbook

Vulnerability
  1. Detect

    Identify every host running the affected component and compare the installed build against the fixed version below — for source-built or distro-packaged software the version string, not a lockfile, is the source of truth (`dpkg -l`, `rpm -q`, or the binary's own `--version`).

  2. Remediation status

    No fixed release is recorded for CVE-2026-114612 yet. Track the upstream advisory, and apply the exposure-reduction steps below in the meantime.

  3. Mitigate without a patch

    Close the privilege gap rather than the entry point: audit which accounts, roles and service identities can reach the affected operation, drop the component to the least privilege it actually needs, and review file and directory permissions created by earlier installs — a default left in place is what makes this reachable.

Frequently Asked Questions

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted metadata containing a forged administrator credential encrypted and returned by the API-key flow. Replaying that ciphertext as a bearer token causes the proxy to trust the forged proxy administrator identity, permitting administrative access and arbitrary commands through the MCP stdio endpoint. Versio
O3 Security · Impact-Aware SCA

Is CVE-2026-114612 in your dependencies?

Find it across , including transitive dependencies.