Vulnerability 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.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Litellm | Litellm | <= 1.82.5 |
Related Weaknesses (CWE)
References
- https://gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817aExploitThird Party Advisory
- https://vuldb.com/cve/CVE-2026-12797Third Party AdvisoryVDB Entry
- https://vuldb.com/submit/811288Third Party AdvisoryExploitVDB Entry
- https://vuldb.com/vuln/372559Third Party AdvisoryVDB Entry
- https://vuldb.com/vuln/372559/ctiPermissions RequiredVDB Entry
FAQ
What is CVE-2026-12797?
CVE-2026-12797 is a vulnerability with a CVSS score of 6.3 (MEDIUM). 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 Completion...
How severe is CVE-2026-12797?
CVE-2026-12797 has been rated MEDIUM with a CVSS base score of 6.3/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-12797?
Check the references section above for vendor advisories and patch information. Affected products include: Litellm Litellm.