CVE-2026-114612BerriAI litellm >= 1.87.0, Improper Privilege Management
NVDCVSS scored by security-advisories@github.com
Vulnerability Summary
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.
CVSS v3.1 Base Metrics — Score 9.9 (CRITICAL)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:HAttack VectorNetwork
Attack ComplexityLow
Privileges RequiredLow
User InteractionNone
ScopeChanged
ConfidentialityHigh
IntegrityHigh
AvailabilityHigh
Affected & Patched Versions
- BerriAI litellm >= 1.87.0, < 1.100.4
- BerriAI litellm >= 1.101.0, < 1.101.3
- BerriAI litellm >= 1.102.0, < 1.102.2
- BerriAI litellm >= 1.103.0, < 1.103.1
- BerriAI litellm >= 1.104.0-rc.1, < 1.104.0-rc.2
No patched version published yet
Until a fix ships, reduce exposure:
- Restrict access to the affected service or interface to trusted networks.
- Disable the affected feature if you do not need it.
- Watch the vendor advisory for a firmware or software update.
What to do
Plan remediation soon. No exploitation is confirmed yet, but the severity is critical.
- Check whether you run BerriAI litellm >= 1.87.0, and which version.
- No patched version is listed yet. Limit access to the affected service to trusted networks, and disable the feature if you can.
- Subscribe to the vendor advisory so you learn when a fix ships.
Timeline
- Oct 22, 2026Published
- Oct 30, 2026Record last modified
Score, severity and exploitation changes are tracked from the day Watchtower started logging them.
Get notified about new BerriAI litellm >= 1.87.0, CVEsYou are reading CVE-2026-114612. Get an email when KEV listings, exploits or new CVEs match your stack.
Set up CVE alertsExternal References
- Patchhttps://github.com/BerriAI/litellm/commit/1d5fdc87fed66b49e1df8cf7d708ad93249eb7d0
- Patchhttps://github.com/BerriAI/litellm/commit/9161d7f9d6073603ba61ee4aa5e2c0ef5b37a81b
- Patchhttps://github.com/BerriAI/litellm/commit/9fa1a641119dd0d4fe43e93622eae5f482ceb63f
- Patchhttps://github.com/BerriAI/litellm/commit/a80eacacee118fbed54e3d98f239d17a63fac818
- Patchhttps://github.com/BerriAI/litellm/commit/f7cd90f09e9716652b38daec9f0640cdf49d582b
- Referencehttps://github.com/BerriAI/litellm/releases/tag/v1.100.4
- Referencehttps://github.com/BerriAI/litellm/releases/tag/v1.101.3
- Referencehttps://github.com/BerriAI/litellm/releases/tag/v1.102.2
- Referencehttps://github.com/BerriAI/litellm/releases/tag/v1.103.1
- Referencehttps://github.com/BerriAI/litellm/releases/tag/v1.104.0-rc.2
- Vendor Advisoryhttps://github.com/BerriAI/litellm/security/advisories/GHSA-7hp6-4w63-5g45
Data last checked: Oct 22, 2026 18:34 UTC