TI-2026-10935 Aliases CVE-2026-12797 GHSA-p897-vf7j-f5h8

BerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization

MEDIUM 57CWE-285Published 2026-06-21 · Updated 2026-06-22

Key facts

Attack vector: Network
Privileges required: Low
User interaction: None
Attack complexity: Low
Attack requirements: None
Impact type: Security bypass
Confidentiality · integrity · availability: Low · Low · Low
Fix status: Deferred Red Hat: fix deferred

Attack profile from CVSS 4.0 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-285.

Summary

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV

EPSS 0.004 34th percentileScored 2026-11-07

Public exploit Yes 1 exploit referenceTagged by the CNA and NVD

Fix Deferred Red Hat: fix deferred

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation: Poc
Automatable: No
Technical impact: Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

Vendor	Product	Affected versions	Fixed in	Status	Source
BerriAI	litellm	1.82.0; 1.82.1; 1.82.2; 1.82.3; 1.82.4; 1.82.5	—	No fix listed	CNA
—	litellm (PyPI)	up to 1.82.5	—	No fix listed	GHSA-p897-vf7j-f5h8

litellm VendorBerriAI Affected 1.82.0; 1.82.1; 1.82.2; 1.82.3; 1.82.4; 1.82.5 Fixed in — No fix listed CNA
litellm (PyPI) Vendor— Affected up to 1.82.5 Fixed in — No fix listed GHSA-p897-vf7j-f5h8

CPE configurations NVD · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:litellm:litellm::::::::	up to 1.82.5	Vulnerable	BerriAI

cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* Versions up to 1.82.5 Vulnerable ·BerriAI

Remediation

No fixed version listed by the sources yet.

Vendor assessments

Red Hat

Red Hat rating: Low. Red Hat's page for this CVE →

Product	Status	Plan or fix
Exploit Intelligence	Affected	No fix yet: Fix deferred
Red Hat Ansible Automation Platform 2	Affected	No fix yet: Fix deferred
Red Hat OpenShift AI (RHOAI)	Affected	No fix yet: Fix deferred

Timeline

2026-10-02 Threatist record created from CVE-2026-12797
2026-10-03 Alias added: GHSA-p897-vf7j-f5h8

References

TI-2026-26015 Trivy ecosystem supply chain briefly compromised KEVCVSS 4.0CRITICAL 9.4
TI-2026-30529 LiteLLM: SQL injection in Proxy API key verification KEVCVSS 4.0CRITICAL 9.3
TI-2026-30582 LiteLLM: Authenticated command execution via MCP stdio test endpoints KEVCVSS 4.0HIGH 8.7
TI-2026-42639 LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback KEVCVSS 4.0HIGH 8.8
TI-2024-05340 Remote Code Execution in BerriAI/litellm CVSS 3.1CRITICAL 9.8
TI-2024-02760 Server-Side Template Injection in BerriAI/litellm CVSS 3.0CRITICAL 9.8

See all 36 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences