CVE-2026-47101: LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that t

Q: How do I fix CVE-2026-47101?

litellm: upgrade to 1.83.14. Exact commands for each OS are on this page.

Q: Is CVE-2026-47101 being exploited?

CVE-2026-47101 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.

Q: What does CVE-2026-47101 affect?

CVE-2026-47101 affects litellm. Severity is high (CVSS 8.8). LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit. When generating a key, the allowed_routes field is stored without verifying that the specified routes f

Q: How urgent is CVE-2026-47101?

Priority 53/100. High severity; Public exploit reference

This month

HIGH 8.8UPGRADE

CVE-2026-47101 is a high-severity flaw (CVSS 8.8) affecting litellm. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.

LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit. When generating a key, the allowed_routes field is stored without verifying that the specified routes fall within the user's own permissions. A key created with access to admin-only routes can then be used to reach those routes successfully, bypassing the role-based access controls that would otherwise block the

Why this priority

High severity
Public exploit reference

A fixed release or distro patch exists.

Risk facts

CVSS score	8.8 (High)
Attack vector	Network (remote)
Attack complexity	Low
Privileges needed	Low
User interaction	None
EPSS exploit chance	1.2% (top 32%)
CISA exploited list	No
Weakness	CWE-863, CWE-639
Published	2026-05-21
Last modified	2026-10-08

Publisher (CNA): VulnCheck · Vendor: litellm

Last updated 2026-10-08 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score

Am I affected?

Timeline

2026-05-21 21:16 UTCPublished CVE record published
2026-10-08 16:17 UTCUpdated Record last modified

litellm litellm UPGRADE

Affected: < 1.83.14

Fixed in: 1.83.14

Safe to downgrade to: no unaffected older release

1. Check installed version

apt-cache policy litellm || rpm -q litellm || litellm --version

2. UPGRADE to 1.83.14 (Debian / Ubuntu)

sudo apt update && sudo apt install --only-upgrade litellm

2. UPGRADE (RHEL / Amazon Linux / Fedora)

sudo dnf upgrade litellm

Note

Distros often backport fixes without changing the version number. Confirm with the distro advisory or changelog.

Verify at the official source NVD · CVE Program · Report a problem with this page
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.

Quick answers

How do I fix CVE-2026-47101?

litellm: upgrade to 1.83.14. Exact commands for each OS are on this page.

Is CVE-2026-47101 being exploited?

CVE-2026-47101 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.

What does CVE-2026-47101 affect?

CVE-2026-47101 affects litellm. Severity is high (CVSS 8.8). LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit. When generating a key, the allowed_routes field is stored without verifying that the specified routes f

How urgent is CVE-2026-47101?

Priority 53/100. High severity; Public exploit reference

Related CVEs

CVE-2026-40217 HIGH 8.8 UPGRADE LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /gu
CVE-2026-42208 CRITICAL 9.8 EXPLOITED UPGRADE BerriAI LiteLLM SQL Injection Vulnerability
CVE-2026-42271 HIGH 8.8 EXPLOITED UPGRADE UPGRADE BerriAI LiteLLM Command Injection Vulnerability
CVE-2026-42203 HIGH 8.8 UPGRADE LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format
CVE-2026-49468 CRITICAL 9.8 UPGRADE LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format

References

← Back to latest CVEs