CVE-2026-12797

MEDIUM 6.3

BerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization

CVSS Score

6.3

EPSS Score

0.0%

EPSS Percentile

0th

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.

CWE	CWE-863 CWE-285
Vendor	berriai
Product	litellm
Published	Jun 21, 2026

Stay Ahead of the Next One

Get instant alerts for berriai litellm

Be the first to know when new medium vulnerabilities affecting berriai litellm are published — delivered to Slack, Telegram or Discord.

Get Free Alerts → Free · No credit card · 60 sec setup

CVSS v3 Breakdown

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

Attack Vector

Attack Complexity

Privileges Required

User Interaction

Scope

Confidentiality

Integrity

Availability

Affected Versions

BerriAI / litellm

1.82.0 1.82.1 1.82.2 1.82.3 1.82.4 1.82.5

References

NVD ↗ CVE.org ↗ EPSS Data ↗

vuldb.com: https://vuldb.com/vuln/372559 vuldb.com: https://vuldb.com/vuln/372559/cti vuldb.com: https://vuldb.com/cve/CVE-2026-12797 vuldb.com: https://vuldb.com/submit/811288 gist.github.com: https://gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817a

Credits

🔍 Eric-c (VulDB User) VulDB CNA Team