Medium severity6.3NVD Advisory· Published Jun 21, 2026· Updated Jun 24, 2026
CVE-2026-12797
CVE-2026-12797
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
litellmPyPI | <= 1.82.5 | — |
Affected products
2Patches
Vulnerability mechanics
References
7- gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817anvdExploitThird Party AdvisoryWEB
- github.com/advisories/GHSA-p897-vf7j-f5h8ghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-12797ghsaADVISORY
- vuldb.com/cve/CVE-2026-12797nvdThird Party AdvisoryVDB EntryWEB
- vuldb.com/submit/811288nvdThird Party AdvisoryExploitVDB EntryWEB
- vuldb.com/vuln/372559nvdThird Party AdvisoryVDB EntryWEB
- vuldb.com/vuln/372559/ctinvdPermissions RequiredVDB EntryWEB
News mentions
1- Litellm: Ten Vulnerabilities Including Auth Bypass and SSRF Disclosed TogetherVypr Intelligence · Jun 21, 2026