AI agent vulnerability · LiteLLM

CVE-2026-12797: BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints

lowCVSS 4.0 2.1 · 3.1 6.3GHSA-p897-vf7j-f5h8

A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function asyncprecallhook of the file enterprise/enterprisehooks/bannedkeywords.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.

Published Jun 21, 2026 · Updated Sep 14, 2026

Affected packages

litellm

Ecosystem: PyPI
Affected: <= 1.82.5
Fixed in: No patched version yet
Check: pip show litellm

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LiteLLM vulnerabilities

All LiteLLM entries