A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected 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 results in incorrect authorization. The attack may be performed from remote. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure.
Metrics
Affected Vendors & Products
References
History
Sun, 21 Jun 2026 15:00:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected 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 results in incorrect authorization. The attack may be performed from remote. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure. | |
| Title | BerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization | |
| First Time appeared |
Litellm
Litellm litellm |
|
| Weaknesses | CWE-285 CWE-863 |
|
| CPEs | cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* | |
| Vendors & Products |
Litellm
Litellm litellm |
|
| References |
| |
| Metrics |
cvssV2_0
|
Status: PUBLISHED
Assigner: VulDB
Published:
Updated: 2026-06-21T09:15:08.592Z
Reserved: 2026-06-20T17:12:18.055Z
Link: CVE-2026-12797
No data.
No data.
No data.
OpenCVE Enrichment
Updated: 2026-06-21T16:30:05Z