Lucene search
+L

19 matches found

Kitploit
Kitploit
•added 2026/09/21 1:56 a.m.•12 views

CVE-2026-42203

LiteLLM CVE-2026-42203 PoC 사용 설명 이 문서는 로컬 LiteLLM 환경을 시작하고 CVE-2026-42203.py를 실행하여 /prompts/test SSTI 취약점을 검증하는 방법을 설명합니다. 승인된 로컬 실험 환경에서만 사용하십시오. 스크립트를 승인되지 않은 공용 네트워크 대상으로 지정하지 마십시오. 1. 로컬 환경 시작 Lab 디렉토리로 이동하여 LiteLLM, Postgres 및 Prometheus를 시작합니다: root@kitploit: docker compose up -d 컨테이너 상태 확인...

8.8CVSS6AI score0.00664EPSS
SaveExploits1
OSV
OSV
•added 2026/09/10 9:44 a.m.•6 views

PYSEC-2026-3861 LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint

BerriAI litellm =1.82.4 is vulnerable to Server-Side Template Injection SSTI, which allows unauthenticated remote attackers to execute arbitrary OS commands via a crafted dotpromptcontent parameter in the /prompts/test endpoint due to use of an unsandboxed jinja2.Environment...

9.8CVSS6.5AI score0.00799EPSS
SaveExploits0References8
Github Security Blog
Github Security Blog
•added 2026/08/27 9:31 p.m.•10 views

LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint

BerriAI litellm =1.82.4 is vulnerable to Server-Side Template Injection SSTI, which allows unauthenticated remote attackers to execute arbitrary OS commands via a crafted dotpromptcontent parameter in the /prompts/test endpoint due to use of an unsandboxed jinja2.Environment...

9.8CVSS6.5AI score0.00799EPSS
SaveExploits0References6Affected Software1
OSV
OSV
•added 2026/07/13 3:02 p.m.•11 views

PYSEC-2026-2602 LiteLLM: Server-Side Template Injection in /prompts/test endpoint

Impact The POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user cou...

8.6CVSS6.2AI score0.00664EPSS
SaveExploits1References6
PyPA
PyPA
•added 2026/07/13 3:02 p.m.•22 views

LiteLLM: Server-Side Template Injection in /prompts/test endpoint

ImpactThe POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process.The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could...

8.8CVSS6.2AI score0.00664EPSS
SaveExploits1References6Affected Software1
Positive Technologies
Positive Technologies
•added 2026/07/13 12:00 a.m.•30 views

PT-2026-59256

Impact The POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user cou...

8.8CVSS6.2AI score0.00664EPSS
SaveExploits1References7
RedhatCVE
RedhatCVE
•added 2026/05/13 12:43 p.m.•44 views

CVE-2026-42203

A flaw was found in LiteLLM, an AI Gateway. An authenticated user could exploit this by sending a crafted prompt template to the POST /prompts/test endpoint. The endpoint rendered user-supplied prompt templates without proper sandboxing. This could lead to arbitrary code execution within the...

8.8CVSS6.2AI score0.00664EPSS
SaveExploits1References5
Veracode
Veracode
•added 2026/05/09 5:40 a.m.•26 views

Remote Code Execution (RCE)

LiteLLM is vulnerable to Remote Code Execution RCE. The vulnerability is due to unsafe rendering of user-supplied prompt templates in the POST /prompts/test endpoint without sandboxing, allowing authenticated users to execute arbitrary code within the LiteLLM Proxy process and potentially access...

8.8CVSS6.2AI score0.00664EPSS
SaveExploits1References7Affected Software1
Cvelist
Cvelist
•added 2026/05/08 3:36 a.m.•75 views

CVE-2026-42203 LiteLLM: Server-Side Template Injection in /prompts/test endpoint

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the...

8.6CVSS0.00664EPSS
SaveExploits1References2
CVE
CVE
•added 2026/05/08 3:36 a.m.•112 views

CVE-2026-42203

LiteLLM (proxy server) is affected from version 1.80.5 up to before 1.83.7 due to Server-Side Template Injection in the POST /prompts/test endpoint. The endpoint renders user-supplied prompt templates without sandboxing, enabling arbitrary code execution inside the LiteLLM Proxy process when auth...

8.8CVSS6AI score0.00664EPSS
SaveExploits1References5Affected Software1
OSV
OSV
•added 2026/05/08 3:36 a.m.•12 views

CVE-2026-42203 LiteLLM: Server-Side Template Injection in /prompts/test endpoint

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the...

8.6CVSS6.1AI score
SaveExploits0References7
EUVD
EUVD
•added 2026/05/08 3:36 a.m.•30 views

EUVD-2026-28502

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the...

8.6CVSS6AI score0.00664EPSS
SaveExploits1References2
Vulnrichment
Vulnrichment
•added 2026/05/08 3:36 a.m.•14 views

CVE-2026-42203 LiteLLM: Server-Side Template Injection in /prompts/test endpoint

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the...

8.6CVSS6AI score0.00664EPSS
SaveExploits1References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/05/08 12:00 a.m.•0 views

CVE-2026-42203: Improper Neutralization of Special Elements Used in a Template Engine

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the...

8.8CVSS6AI score0.00664EPSS
SaveExploits1References4
CNNVD
CNNVD
•added 2026/05/08 12:00 a.m.•25 views

LiteLLM 安全漏洞

LiteLLM is an open-source application developed by Berri AI. It allows for the invocation of all LLM APIs in the OpenAI format. Versions of LiteLLM from 1.80.5 to 1.83.7 contained a security vulnerability. This vulnerability stemmed from the POST /prompts/test endpoint accepting user-provided...

8.8CVSS6.3AI score0.00664EPSS
SaveExploits1References1
Snyk
Snyk
•added 2026/04/24 4:02 p.m.•28 views

Improper Neutralization of Special Elements Used in a Template Engine

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Improper Neutralization of Special Elements Used in a Template Engine via the POST /prompts/test endpoint, which accepts user-supplied prompt templates and renders them...

8.8CVSS6.2AI score0.00664EPSS
SaveExploits1References2
Github Security Blog
Github Security Blog
•added 2026/04/24 4:02 p.m.•48 views

LiteLLM: Server-Side Template Injection in /prompts/test endpoint

Impact The POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user cou...

8.8CVSS5.9AI score0.00664EPSS
SaveExploits1References4Affected Software1
OSV
OSV
•added 2026/04/24 4:02 p.m.•34 views

GHSA-XQMJ-J6MV-4862 LiteLLM: Server-Side Template Injection in /prompts/test endpoint

Impact The POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user cou...

8.6CVSS5.9AI score0.00664EPSS
SaveExploits1References4
EUVD
EUVD
•added 2025/11/12 4:29 a.m.•11 views

EUVD-2025-111189

Malicious code in meteor-pulsar-prompts-test npm...

6.6AI score
SaveExploits0
Rows per page
Query Builder