LiteLLM: critical vulnerability

LiteLLM

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…

Do this now

Upgrade litellm to 1.103.1, 1.102.2 or 1.101.3, matching your release line (more lines in the table).

Fix it

litellm pip

On 1.100.x?pip install --upgrade "litellm>=1.100.4,<1.101"
On 1.101.x?pip install --upgrade "litellm>=1.101.3,<1.102"
On 1.102.x?pip install --upgrade "litellm>=1.102.2,<1.103"
On 1.103.x?pip install --upgrade "litellm>=1.103.1,<1.104"
On 1.104.xNo stable fix for 1.104.x yet (only 1.104.0rc2)

First seen: 24 Oct 2026
Last update: 24 Oct 2026, 16:17 UTC
Fixed in: litellm 1.104.0rc2
litellm 1.103.1
litellm 1.102.2
litellm 1.101.3
litellm 1.100.4
Identifiers: CVE-2026-114612
CVSS: 9.9
Source: news
On the menu as: LLM gateways
PyPI packages

Check this repository for exposure to one security incident from pwned.coffee. Report first, change nothing until I say so.

## LiteLLM: critical vulnerability
Severity: critical. Patch status: patched.
Affected: LiteLLM
Fixed in: litellm 1.104.0rc2, litellm 1.103.1, litellm 1.102.2, litellm 1.101.3, litellm 1.100.4
Ids: CVE-2026-114612

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…

## Steps
1. Search every lockfile and manifest (package-lock.json, yarn.lock, pnpm-lock.yaml, requirements*.txt, poetry.lock, uv.lock, composer.lock, go.sum, Cargo.lock, Gemfile.lock) for `litellm`. For each hit, compare the installed version with the fix on the same major line: litellm 1.104.0rc2, litellm 1.103.1, litellm 1.102.2, litellm 1.101.3, litellm 1.100.4. If it's lower, give the exact upgrade command for the package manager this repo uses.
2. This incident involves a provider (ai-gateways). Search config, CI and env templates (.env.example, wrangler.toml, vercel.json, terraform, workflow secrets) for credentials stored there. List each secret by name, where it is used, and how to rotate it. Never print secret values.

## Report
A table: file, product or package, version in use, affected yes/no, exact fix. Then anything a human has to check outside the repo.

If you have the pwned.coffee MCP server (https://pwned.coffee/mcp), call lookup_cve("CVE-2026-114612") for the latest, and check_repo with this repo's lockfiles, Dockerfiles and workflows for a full receipt.
Sources: https://github.com/BerriAI/litellm/commit/1d5fdc87fed66b49e1df8cf7d708ad93249eb7d0 https://nvd.nist.gov/vuln/detail/CVE-2026-114612
https://pwned.coffee/i/litellm-security-advisory-cve-2026-114612

Timeline

24 Oct 2026, 16:17 UTC
Fix status: unknown → patched.
24 Oct 2026
First reported.

Receipt

Exploitation: No known exploitation
Fix by release line: Product Affected Fixed in Source
litellm (pip) >= 1.104.0rc1, < 1.104.0rc2 1.104.0rc2 GitHub advisory
litellm (pip) >= 1.103.0, <1.103.1 1.103.1 GitHub advisory
litellm (pip) >= 1.102.0, < 1.102.2 1.102.2 GitHub advisory
litellm (pip) >= 1.101.0, < 1.101.3 1.101.3 GitHub advisory
litellm (pip) >= 1.91.0, < 1.100.4 1.100.4 GitHub advisory
Score: CVSS 9.9 (critical). CVSS 3.1 9.9 (CNA GitHub_M) for CVE-2026-114612
Last checked: 24 Oct 2026, 16:25 UTC

Product	Affected	Fixed in	Source
litellm (pip)	>= 1.104.0rc1, < 1.104.0rc2	1.104.0rc2	GitHub advisory
litellm (pip)	>= 1.103.0, <1.103.1	1.103.1	GitHub advisory
litellm (pip)	>= 1.102.0, < 1.102.2	1.102.2	GitHub advisory
litellm (pip)	>= 1.101.0, < 1.101.3	1.101.3	GitHub advisory
litellm (pip)	>= 1.91.0, < 1.100.4	1.100.4	GitHub advisory

Sources: KEV – CVE record ✓ Vendor ✓

Sources

Totalone very hot coffee