Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

redhat логотип

CVE-2026-12797

Опубликовано: 21 июн. 2026
Источник: redhat
CVSS3: 4.3

Описание

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.

A flaw was found in BerriAI litellm. A remote attacker could manipulate the prompt argument in the async_pre_call_hook function of the Completions Interface component. This manipulation leads to incorrect authorization, potentially allowing the attacker to bypass security controls and perform unauthorized actions within the system. Administrators for the LLM proxy believe their blocklist and content-safety checks are active, but no input validation actually runs.

Отчет

This is a confidence/integrity-of-controls problem, not a path to code execution or data exfiltration.

Затронутые пакеты

ПлатформаПакетСостояниеРекомендацияРелиз
Exploit Intelligenceexploit-intelligence-tech-preview/vulnerability-analysis-rhel9Fix deferred
Red Hat Ansible Automation Platform 2ansible-automation-platform-26/lightspeed-chatbot-rhel9Fix deferred
Red Hat Ansible Automation Platform 2ansible-automation-platform-27/lightspeed-chatbot-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-llama-stack-core-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-mlflow-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9Fix deferred

Показывать по

Дополнительная информация

Статус:

Low
Дефект:
CWE-551
https://bugzilla.redhat.com/show_bug.cgi?id=2491142litellm: BerriAI litellm: Incorrect authorization via prompt manipulation

4.3 Medium

CVSS3

Связанные уязвимости

CVSS3: 6.3
nvd
около 2 месяцев назад

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.

CVSS3: 6.3
github
около 2 месяцев назад

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.

4.3 Medium

CVSS3