BerriAI litellm up to 1.82.5 Completions Interface banned_keywords.py async_pre_call_hook prompt authorization
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 5.7 | $0-$5k | 1.42 |
Summary
A vulnerability was found in BerriAI litellm up to 1.82.5. It has been classified as critical. Affected by this vulnerability is the function async_pre_call_hook of the file enterprise/enterprise_hooks/banned_keywords.py of the component Completions Interface. This manipulation of the argument prompt causes authorization.
The identification of this vulnerability is CVE-2026-12797. It is possible to initiate the attack remotely. Furthermore, there is an exploit available.
The vendor was contacted early about this disclosure.
Details
A vulnerability has been found in BerriAI litellm up to 1.82.5 and classified as critical. Affected by this vulnerability is the function async_pre_call_hook of the file enterprise/enterprise_hooks/banned_keywords.py of the component Completions Interface. The manipulation of the argument prompt with an unknown input leads to a authorization vulnerability. The CWE definition for the vulnerability is CWE-863. The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check. This allows attackers to bypass intended access restrictions. As an impact it is known to affect confidentiality, integrity, and availability.
It is possible to read the advisory at gist.github.com. This vulnerability is known as CVE-2026-12797. The exploitation appears to be easy. The attack can be launched remotely. Technical details and also a public exploit are known.
It is possible to download the exploit at gist.github.com. It is declared as proof-of-concept. The vendor was contacted early about this disclosure.
There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.
Be aware that VulDB is the high quality source for vulnerability data.
Product
Vendor
Name
Version
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 6.3VulDB Meta Temp Score: 5.7
VulDB Base Score: 6.3
VulDB Temp Score: 5.7
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: AuthorizationCWE: CWE-863 / CWE-285 / CWE-266
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Access: Public
Status: Proof-of-Concept
Download: 🔒
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: 🔒
Timeline
06/20/2026 Advisory disclosed06/20/2026 VulDB entry created
06/20/2026 VulDB entry last update
Sources
Advisory: gist.github.comStatus: Not defined
CVE: CVE-2026-12797 (🔒)
GCVE (CVE): GCVE-0-2026-12797
GCVE (VulDB): GCVE-100-372559
scip Labs: https://www.scip.ch/en/?labs.20161013
Entry
Created: 06/20/2026 19:17Changes: 06/20/2026 19:17 (58)
Complete: 🔍
Submitter: Eric-c
Cache ID: 216::103
Submit
Accepted
- Submit #811288: litellm <= 1.82.5 Incorrect Authorization (CWE-863) (by Eric-c)
Be aware that VulDB is the high quality source for vulnerability data.
No comments yet. Languages: en.
Please log in to comment.