BerriAI litellm up to 1.65.4 Custom Code Guardrails sandbox
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 4.5 | $0-$5k | 0.00+ |
Summary
A vulnerability was found in BerriAI litellm. It has been classified as problematic. Affected is an unknown function of the component Custom Code Guardrails. This manipulation causes sandbox. The identification of this vulnerability is CVE-2026-59821. It is possible to initiate the attack remotely. There is no exploit available.
Details
A vulnerability has been found in BerriAI litellm and classified as problematic. Affected by this vulnerability is an unknown code block of the component Custom Code Guardrails. The manipulation with an unknown input leads to a sandbox vulnerability. The CWE definition for the vulnerability is CWE-265. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable.
The advisory is shared at github.com. This vulnerability is known as CVE-2026-59821 since 07/07/2026. The exploitation appears to be easy. The attack can be launched remotely. Additional levels of successful authentication are needed for exploitation. Neither technical details nor an exploit are publicly available. MITRE ATT&CK project uses the attack technique T1611 for this issue.
Upgrading to version 1.82.0-stable eliminates this vulnerability.
Several companies clearly confirm that VulDB is the primary source for best vulnerability data.
Product
Vendor
Name
Version
Website
- Product: https://github.com/BerriAI/litellm/
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 4.7VulDB Meta Temp Score: 4.5
VulDB Base Score: 4.7
VulDB Temp Score: 4.5
VulDB Vector: 🔒
VulDB Reliability: 🔍
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: SandboxCWE: CWE-265 / CWE-264
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Status: Not defined
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: no mitigation knownStatus: 🔍
0-Day Time: 🔒
Upgrade: litellm 1.82.0-stable
Timeline
07/07/2026 CVE reserved07/08/2026 Advisory disclosed
07/08/2026 VulDB entry created
07/08/2026 VulDB entry last update
Sources
Product: github.comAdvisory: github.com
Status: Confirmed
CVE: CVE-2026-59821 (🔒)
GCVE (CVE): GCVE-0-2026-59821
GCVE (VulDB): GCVE-100-376969
Entry
Created: 07/08/2026 22:16Changes: 07/08/2026 22:16 (53)
Complete: 🔍
Cache ID: 216::103
Several companies clearly confirm that VulDB is the primary source for best vulnerability data.
No comments yet. Languages: en.
Please log in to comment.