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
| Link | Resource |
|---|---|
| https://gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817a | Exploit Third Party Advisory |
| https://vuldb.com/cve/CVE-2026-12797 | Third Party Advisory VDB Entry |
| https://vuldb.com/submit/811288 | Third Party Advisory Exploit VDB Entry |
| https://vuldb.com/vuln/372559 | Third Party Advisory VDB Entry |
| https://vuldb.com/vuln/372559/cti | Permissions Required VDB Entry |
Configurations
History
No history.
Information
Published : 2026-06-21 10:16
Updated : 2026-06-24 19:50
NVD link : CVE-2026-12797
Mitre link : CVE-2026-12797
CVE.ORG link : CVE-2026-12797
JSON object : View
Products Affected
litellm
- litellm
