Tag
LiteLLM Remote Code Execution via Bytecode Rewriting (CVE-2026-40217)
2 rules 1 TTP 1 CVELiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI, potentially leading to complete system compromise.
LiteLLM Authentication Bypass via Password Hash Exposure and Pass-the-Hash
2 rules 1 TTPLiteLLM versions before 1.83.0 stored user passwords as unsalted SHA-256 hashes and exposed these hashes through multiple API endpoints, enabling an authenticated user to retrieve another user's password hash and use it to log in as that user due to the /v2/login endpoint accepting the raw SHA-256 hash without re-hashing, leading to potential privilege escalation.
Compromised Litellm PyPI Package Versions
2 rules 4 TTPs 1 IOCVersions 1.82.7 and 1.82.8 of the Litellm package on PyPI were compromised in a supply chain attack, potentially impacting numerous users, with recommendations to avoid updating to these versions.
LiteLLM Proxy API Key Verification SQL Injection
2 rules 1 TTPA SQL injection vulnerability exists in LiteLLM versions 1.81.16 to prior to 1.83.7 allowing an unauthenticated attacker to inject SQL queries via a crafted 'Authorization' header, potentially leading to unauthorized data access or modification.
LiteLLM Server-Side Template Injection Vulnerability
2 rules 1 TTPA server-side template injection vulnerability in LiteLLM versions 1.80.5 to before 1.83.7 allows authenticated users to execute arbitrary code within the LiteLLM Proxy process via a crafted prompt template, potentially exposing sensitive information and enabling command execution on the host.
LiteLLM Authenticated Command Execution via MCP stdio Test Endpoints
2 rules 1 TTPAuthenticated users with low-privilege API keys could execute arbitrary commands on the host running LiteLLM via the `/mcp-rest/test/connection` and `/mcp-rest/test/tools/list` endpoints, by submitting a server configuration including command execution parameters.