Log in Start free

Vulnerability · Published Jun 21, 2026 · Assigned by VulDB

CVE-2026-12797BerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization

Medium 6.3

In plain English

A medium-severity incorrect authorization in litellm from BerriAI. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 34% of all known vulnerabilities).

Severity (CVSS 3.1)6.3Medium
Exploit odds (30 days)0.4%top 65.6% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official description

A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function async_pre_call_hook of the file enterprise/enterprise_hooks/banned_keywords.py of the component Completions Interface. The manipulation of the argument prompt results in incorrect authorization. The attack may be performed from remote. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIlitellmno fix listedGHSA-p897-vf7j-f5h8
PyPIlitellmno fix listedPYSEC-2026-4074

Affected products (as reported)

VendorProductVersions
BerriAI litellm 1.82.01.82.11.82.21.82.31.82.41.82.5

Weakness: CWE-863, CWE-285 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R

References