Arbitrary file deletion in litellm

BerriAI's litellm, in its latest version, is vulnerable to arbitrary file deletion due to improper input validation on the /audio/transcriptions endpoint. An attacker can exploit this vulnerability by sending a specially crafted request that includes a file path to the server, which then deletes...

SQL injection in litellm

An SQL Injection vulnerability exists in the berriai/litellm repository, specifically within the /global/spend/logs endpoint. The vulnerability arises due to improper neutralization of special elements used in an SQL command. The affected code constructs an SQL query by concatenating an unvalidat...

PYSEC-2026-1544 SQL injection in litellm

A blind SQL injection vulnerability exists in the berriai/litellm application, specifically within the '/team/update' process. The vulnerability arises due to the improper handling of the 'userid' parameter in the raw SQL query used for deleting users. An attacker can exploit this vulnerability b...

litellm passes untrusted data to `eval` function without sanitization

A remote code execution RCE vulnerability exists in the berriai/litellm project due to improper control of the generation of code when using the eval function unsafely in the litellm.getsecret method. Specifically, when the server utilizes Google KMS, untrusted data is passed to the eval function...

Exploit for Authentication Bypass by Spoofing in Litellm

CVE-2026-49468 — LiteLLM Unauthenticated Auth Bypass via Host-...

LiteLLM Detection

A LiteLLM Python library is installed on the remote host. Note that Nessus has relied upon on the application's self-reported version number. %NASLMINLEVEL 80900 C Tenable, Inc. include'compat.inc'; if description scriptid324116; scriptversion"1.1";...

PYSEC-2026-388 LiteLLM: Authentication Bypass via Host Header Injection

Impact A Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from request.url.path in litellm/proxy/auth/authutils.py::getrequestroute, which Starlette reconstructs...

LiteLLM: Authentication Bypass via Host Header Injection

ImpactA Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from request.url.path in litellm/proxy/auth/authutils.py::getrequestroute, which Starlette reconstructs...

LiteLLM has SQL Injection in Proxy API key verification

ImpactA database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route for example POST /chat/completions an...

0xpwn (0.1.1), a2a-acl (0.0.14) +243 more potentially affected by CVE-2026-42208 via litellm (>=1.81.16, <=1.83.4)

litellm PYPI version =1.81.16, =0.7.3, =0.1.46, =0.25.4a2, =0.1.2, =0.1.0a6, =0.1.0, =0.1.14.13, =0.0.0.post0, =0.5.2, =0.1.0, =0.3.1 and more Source cves: CVE-2026-42208 Source advisory: OSV:PYSEC-2026-391...

litellm vulnerable to remote code execution based on using eval unsafely

BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The vulnerability exists in the adddeployment function, which decodes and decrypts environment variables from base64 and assigns them to os.environ. An attacker can exploit this by sendin...

PYSEC-2026-389 litellm vulnerable to remote code execution based on using eval unsafely

BerriAI/litellm version v1.35.8 contains a vulnerability where an attacker can achieve remote code execution. The vulnerability exists in the adddeployment function, which decodes and decrypts environment variables from base64 and assigns them to os.environ. An attacker can exploit this by sendin...

LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint

BerriAI/litellm is vulnerable to Server-Side Template Injection SSTI via the /completions endpoint. The vulnerability arises from the hfchattemplate method processing the chattemplate parameter from the tokenizerconfig.json file through the Jinja template engine without proper sanitization...

PYSEC-2026-387 LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint

BerriAI/litellm is vulnerable to Server-Side Template Injection SSTI via the /completions endpoint. The vulnerability arises from the hfchattemplate method processing the chattemplate parameter from the tokenizerconfig.json file through the Jinja template engine without proper sanitization...

CVE-2026-12772

A flaw was found in BerriAI litellm. A remote attacker could exploit a vulnerability in the authenticateuser function within the PROXYADMIN database API Key Generator component. By performing a specific manipulation, an attacker can cause session expiration for users, leading to a denial of servi...

PT-2026-53473

Impact A Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from request.url.path in litellm/proxy/auth/auth utils.py::get request route, which Starlette reconstruc...

semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin

Impact semantic-router versions 0.1.8 through 0.1.14 declare litellm=1.61.3 with no upper bound. During the window in which litellm==1.82.8 was the latest release on PyPI, a fresh install of any affected semantic-router version could resolve to that compromised wheel. The malicious litellm==1.82....

GHSA-98X5-VQ43-VC5P semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin

Impact semantic-router versions 0.1.8 through 0.1.14 declare litellm=1.61.3 with no upper bound. During the window in which litellm==1.82.8 was the latest release on PyPI, a fresh install of any affected semantic-router version could resolve to that compromised wheel. The malicious litellm==1.82....

Weekly Metasploit Update: Modules for Audiobookshelf, LiteLLM, Next.js, Dalfox and more

Help shape the future of Metasploit Framework We are planning future work in relation to the evasion capabilities present in Metasploit Framework, and how they function/are presented to users. We are currently accepting responses to our feedback form, which means that you can shape the future of...

CVE-2026-12773

A flaw was found in BerriAI litellm, within its MCP Proxy component. A remote attacker could exploit an improper authentication vulnerability in the UserAPIKeyAuth function. This could allow unauthorized access, potentially compromising the confidentiality, integrity, and availability of data...