LiteLLM arbitrary code execution via bytecode rewriting
CVE-2026-40217High
LiteLLM contains a flaw in the /guardrails/test_custom_code endpoint that allows remote attackers to execute arbitrary code through bytecode rewriting. An attacker can send a request to this endpoint to achieve code execution on the affected system. No authentication or special privileges are required to exploit this vulnerability.
Plain English summary of the NVD and CISA text, checked by machine against both.
Scores and dates
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Detail
Affected versions
- litellm litellm: up to 2026-04-08
Reports naming this CVE2 in total
· Google Threat Intelligence
GTIG AI Threat Tracker: Agentic Threat Activity Crosses a Significant Threshold (opens in a new tab)· Google Threat Intelligence
The Rise of LLMJacking: How Threat Actors Monetize Compromised Cloud and Model Resources (opens in a new tab)