CVE-2026-12797
A security flaw has been discovered in BerriAI litellm up to …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817a
- vuldb.com/cve/CVE-2026-12797
- vuldb.com/submit/811288
- vuldb.com/vuln/372559
- vuldb.com/vuln/372559/cti
- nvd.nist.gov/vuln/detail/CVE-2026-12797
- github.com/advisories/GHSA-p897-vf7j-f5h8
- nvd.nist.gov/vuln/detail/CVE-2026-12797
- cve.org/CVERecord?id=CVE-2026-12797
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.