CVE-2026-40217 · NVD published 10 Apr 2026
BerriAI LiteLLM
On CISA's KEV list 222 days after disclosure; 1 public exploit.
LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI.
CISA required action (federal due date 2 Dec 2026): Apply mitigations in accordance with vendor instructions, ensuring compliance with CISA’s BOD 26-04 Prioritizing Security Updates Based on Risk (see URL in Notes) guidance and CISA’s “Forensics Triage Requirements” (see URL in Notes). Follow applicable BOD 26-04 guidance for cloud services or discontinue use of the product if mitigations are unavailable. Stakeholders are responsible for evaluating each asset's internet exposure and ensuring adherence to BOD 26-04 patching guidelines.
Signals
- KEV, exploited in the wild
- yes, added 18 Nov 2026, due 2 Dec 2026
- EPSS, 30-day forecast
- 17%, 97th percentile (as of 18 Nov 2026)
- CVSS, NVD, HIGH
- 8.8
- Vector
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- Internet exposure
- not stated
KEV is an observation, EPSS a forecast; KEV outranks it.
Timeline 10 Apr 2026 to today
- Disclosed
- First PoC+39 d
- KEV+183 d
183 days from the first proof of concept to the KEV listing
Linked 1 in our graph
Exploited by
- malwareBankshot - S0239
Links our graph holds for this CVE, strongest first. The same data is in the graph API.
Indicators 2 tied by threat feeds
Addresses, hosts and files that threat feeds tag with this CVE: exploitation sources, payload hosts and what was dropped. Defanged. “In rule” marks the ones strong enough for the indicator sweep above.
- jet-night[.]comExploitation infra
domain · Bankshot - S0239 · 3 feeds · last seen 12 Nov 2026
- newapi[.]proExploitation infra
domain · Bankshot - S0239 · 2 feeds · last seen 12 Nov 2026
On the wire 3 dispatches
- Exploited in the wild: CVE-2026-40217 BerriAI LiteLLM Unprotected Alternate Channel Vulnerability Added to CISA KEV · High 8.8 Impacted if: BerriAI LiteLLM bb0639701796218a34 · KEV
- The Rise of LLMJacking: How Threat Actors Monetize Compromised Cloud and Model Resources · KEV
- AI Agents Compromised 440 PaperCut Servers, Researchers Say · KEV
Public exploit code 1 known · links only
GitHub PoCs 1Metasploit 0Exploit-DB 0
GitHub PoCs, by trust then stars1
- learner202649/CVE-2026-40217-PoCTrust ok 1001 stars
The code for personally reproducing the corresponding vulnerability
created 19 May 2026
Fake proof-of-concept repositories have been used to deliver malware to the researchers who run them. The trust verdict is our engine's heuristic over the repository (account age, what it ships, how its stars arrived); it is a reason to read the code first, not a finding about its author.
Nuclei detection templates1
LiteLLM before 1.25.0 allows authenticated users with the master API key to execute arbitrary Python code through the /guardrails/test_custom_code endpoint intended for custom guardrail testing. The endpoint’s insufficient filtering mechanisms can be bypassed, allowing attackers to abuse Python’s string operations and bytecode manipulation to break out of the restricted environment. Successful exploitation may lead to remote code execution as the LiteLLM process user, which may be root when usin
yaml · first seen by skopnix 18 Oct 2026
A Nuclei template is a scanner check that detects the flaw. It is not an exploit and is not counted as one.
References
Watch this one?
KEV additions reach Telegram and the KEV-only RSS as they land.