CVE-2026-12797
MEDIUMBerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization
Title source: cnaDescription
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.
References (5)
Core 5
Core References
Vdb Entry, Technical Description vdb-entry
technical-description
VDB-372559 | BerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization
https://vuldb.com/vuln/372559
Signature, Permissions Required signature
permissions-required
VDB-372559 | CTI Indicators (IOB, IOC, IOA)
https://vuldb.com/vuln/372559/cti
Third Party Advisory third-party-advisory
CVE-2026-12797 | CVE Analysis and Report
https://vuldb.com/cve/CVE-2026-12797
Third Party Advisory third-party-advisory
Submit #811288 | litellm <= 1.82.5 Incorrect Authorization (CWE-863)
https://vuldb.com/submit/811288
Scores
CVSS v3
6.3
EPSS
0.0040
EPSS Percentile
32.8%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
CISA SSVC
Vulnrichment
Exploitation
poc
Automatable
no
Technical Impact
partial
Details
CWE
CWE-285
CWE-863
Status
published
Products (7)
BerriAI/litellm
1.82.0
BerriAI/litellm
1.82.1
BerriAI/litellm
1.82.2
BerriAI/litellm
1.82.3
BerriAI/litellm
1.82.4
BerriAI/litellm
1.82.5
litellm/litellm
< 1.82.5
Published
Jun 21, 2026
Tracked Since
Jun 21, 2026