Advisory

GHSA-p897-vf7j-f5h8

Also known as: CVE-2026-12797, PYSEC-2026-4074

Summary

BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints

Details

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.

Severity

Low Basis: The source's own band: LOW

Dates

Published
2026-06-21 12:30 UTC
Modified
2026-10-01 17:56 UTC

Affected packages and fixes

litellm

PyPI · All systems

Affected

  • introduced 0, last affected 1.82.5 (ecosystem)

Fixed versions

None listed

Fix

No fixed version is listed.

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0

Sources & licences