436 matches found
📄 LiteLLM 1.83.0 Insecure Direct Object Reference
LiteLLM exposes a /config/update API endpoint that allows administrators to make configuration changes to the instance. Due to a missing authorization check, low-privileged users can access this endpoint without restriction. An attacker with a low-privileged account can exploit this to exfiltrate...
CVE-2026-42208
A flaw was found in LiteLLM. A database query used for proxy API key checks incorrectly incorporated caller-supplied key values directly into the query. This vulnerability allows an unauthenticated attacker to send a specially crafted Authorization header to any Large Language Model LLM API route...
Exploit for CVE-2026-42208
LiteLLM Proxy SQL Injection GHSA-r75f-5x8p-qvmc A reproduct...
01os (=0.0.14), 0xpwn (=0.1.1) +627 more potentially affected by CVE-2026-42271 via litellm (>=1.74.3 <=1.83.4)
litellm PYPI version =1.74.3, =0.0.14, =0.0.14, =0.0.1a0, =0.3.5, =0.6.0, =0.7.3, =0.1.0, =0.4.0, =0.1.39, =0.2.1, =0.2.1.10062025 - agent-memory-server =0.15.0 - agent-opt =0.0.1 - agent-quality-inspect =2.0.0a1 and more Source cves: CVE-2026-42271 Source advisory: OSV:GHSA-V4P8-MG3P-G94G...
0xpwn (=0.1.1), a2a-acl (>=0.0.14 <=0.0.15) +265 more potentially affected by CVE-2026-42208 via litellm (>=1.81.16 <=1.83.4)
litellm PYPI version =1.81.16, =0.0.14, =0.0.14, =0.0.1a0, =0.6.0, =0.7.3, =0.1.46, =0.25.4a2, =0.1.0, =0.1.0, =0.1.0, =0.1.14.13, =0.0.0.post0, =2.4.65 and more Source cves: CVE-2026-42208 Source advisory: SNYK:PYTHON-LITELLM-16300164...
0xpwn (=0.1.1), a2a-acl (>=0.0.14 <=0.0.15) +265 more potentially affected by CVE-2026-42208 via litellm (>=1.81.16 <=1.83.4)
litellm PYPI version =1.81.16, =0.0.14, =0.0.14, =0.0.1a0, =0.6.0, =0.7.3, =0.1.46, =0.25.4a2, =0.1.0, =0.1.0, =0.1.0, =0.1.14.13, =0.0.0.post0, =2.4.65 and more Source cves: CVE-2026-42208 Source advisory: OSV:GHSA-R75F-5X8P-QVMC...
SQL Injection
Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to SQL Injection via the token lookup query in the combined view path. An attacker can extract or manipulate records by supplying a crafted token value that is interpolated...
0xpwn (=0.1.1), a2a-acl (>=0.0.14 <=0.0.15) +280 more potentially affected by CVE-2026-42203 via litellm (>=1.80.5 <=1.83.4)
litellm PYPI version =1.80.5, =0.0.14, =0.0.14, =0.0.1a0, =0.6.0, =0.7.3, =0.1.46, =0.25.4a2, =0.1.0, =0.1.0, =0.1.0, =0.0.1, =0.1.14.13, =0.1.17.0 and more Source cves: CVE-2026-42203 Source advisory: OSV:GHSA-XQMJ-J6MV-4862...
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...
0xpwn (=0.1.1), a2a-acl (>=0.0.14 <=0.0.15) +280 more potentially affected by CVE-2026-42203 via litellm (>=1.80.5 <=1.83.4)
litellm PYPI version =1.80.5, =0.0.14, =0.0.14, =0.0.1a0, =0.6.0, =0.7.3, =0.1.46, =0.25.4a2, =0.1.0, =0.1.0, =0.1.0, =0.0.1, =0.1.14.13, =0.1.17.0 and more Source cves: CVE-2026-42203 Source advisory: SNYK:PYTHON-LITELLM-16300055...
PT-2026-37176
Name of the Vulnerable Software and Affected Versions LiteLLM versions 1.80.5 through 1.83.6 Description The 'POST /prompts/test' endpoint accepts user-supplied prompt templates and renders them without sandboxing. An authenticated user with a valid proxy API key can provide a crafted template to...
01os (=0.0.14), 0xpwn (=0.1.1) +627 more potentially affected by CVE-2026-42271 via litellm (>=1.74.3 <=1.83.4)
litellm PYPI version =1.74.3, =0.0.14, =0.0.14, =0.0.1a0, =0.3.5, =0.6.0, =0.7.3, =0.1.0, =0.4.0, =0.1.39, =0.2.1, =0.2.1.10062025 - agent-memory-server =0.15.0 - agent-opt =0.0.1 - agent-quality-inspect =2.0.0a1 and more Source cves: CVE-2026-42271 Source advisory: SNYK:PYTHON-LITELLM-16119122...
Command Injection
Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Command Injection via preview MCP server endpoints POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list. An attacker can execute arbitrary commands by accessin...
Anthropic MCP Design Vulnerability Enables RCE, Threatening AI Supply Chain
Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's MCP architecture that could pave the way for remote code execution and have a cascading effect on the artificial intelligence AI supply chain. "This flaw enables Arbitrary Command Execution R...
GHSA-JJ6C-8H6C-HPPX vulnerabilities
Vulnerabilities for packages: nemo, litellm, open-webui...
GHSA-7GW9-CF7V-778F vulnerabilities
Vulnerabilities for packages: nemo, litellm, open-webui...
GHSA-3CRG-W4F6-42MX vulnerabilities
Vulnerabilities for packages: nemo, litellm, open-webui...
CVE-2026-40260 vulnerabilities
Vulnerabilities for packages: nemo, litellm, open-webui...
GHSA-X284-J5P8-9C5P vulnerabilities
Vulnerabilities for packages: nemo, litellm, open-webui...
GHSA-4PXV-J86V-MHCW vulnerabilities
Vulnerabilities for packages: nemo, litellm, open-webui...