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...

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...

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...

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-X284-J5P8-9C5P vulnerabilities

Vulnerabilities for packages: open-webui, litellm, nemo...

GHSA-JJ6C-8H6C-HPPX vulnerabilities

Vulnerabilities for packages: open-webui, litellm, nemo...

GHSA-7GW9-CF7V-778F vulnerabilities

Vulnerabilities for packages: open-webui, litellm, nemo...

GHSA-4PXV-J86V-MHCW vulnerabilities

Vulnerabilities for packages: open-webui, litellm, nemo...

GHSA-3CRG-W4F6-42MX vulnerabilities

Vulnerabilities for packages: open-webui, litellm, nemo...

CVE-2026-40260 vulnerabilities

Vulnerabilities for packages: open-webui, litellm, nemo...

Duplicate Advisory: LiteLLM has a sandbox escape in custom-code guardrail

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-wxxx-gvqv-xp7p. This link is maintained to preserve external references. Original Description LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the...

GHSA-3926-2JVF-FG29 Duplicate Advisory: LiteLLM has a sandbox escape in custom-code guardrail

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-wxxx-gvqv-xp7p. This link is maintained to preserve external references. Original Description LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the...

CVE-2026-40217

LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/testcustomcode URI...

01os (>=0.0.1 <=0.0.14), 0xpwn (=0.1.1) +826 more potentially affected by CVE-2026-40217 via litellm (>=1.0.0 <=1.83.8)

litellm PYPI version =1.0.0, =0.0.1, =0.0.14, =0.0.14, =0.0.1a0, =0.3.5, =0.6.0, =0.7.3, =0.1.0, =0.4.0, =0.8.1, =0.1.0, =0.1.39, =0.2.1, =0.2.1.10102025 - agent-memory-server =0.15.0 and more Source cves: CVE-2026-40217 Source advisory: SNYK:PYTHON-LITELLM-16049285...

CVE-2026-40217

LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/testcustomcode URI...

CVE-2026-40217

LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/testcustomcode URI...

Arbitrary Code Injection

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Arbitrary Code Injection in the /guardrails/testcustomcode endpoint through bytecode rewriting. An attacker can execute arbitrary code by sending specially crafted requests...

Python Supply-Chain Compromise

This is news: A malicious supply chain compromise has been identified in the Python Package Index package litellm version 1.82.8. The published wheel contains a malicious .pth file litellminit.pth, 34,628 bytes which is automatically executed by the Python interpreter on every startup, without...

01os (>=0.0.1 <=0.0.14), 0xpwn (=0.1.1) +736 more potentially affected by unknown CVE via litellm (>=1.0.0 <=1.82.6)

litellm PYPI version =1.0.0, =0.0.1, =0.0.1a0, =0.3.5, =0.7.3, =0.1.0, =0.4.0, =0.8.1, =0.1.0, =0.1.39, =0.2.1, =0.2.1.10102025 - agent-memory-server =0.15.0 - agent-opt =0.0.1 and more Source cves: unknown CVE Source advisory: SNYK:PYTHON-LITELLM-15928842...

Use of Password Hash With Insufficient Computational Effort

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Use of Password Hash With Insufficient Computational Effort via the user/info, user/update, and spend/users API endpoints, which return password hash fields in responses to...