CVE-2026-12797
mediumpriority · track · 0OT risk · elevatedEPSS 0.004 · 34 %ileEUUSEPSS · scored 2026-10-26
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
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · low–medium · 1.3–6.5
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (8)
Products and version ranges known to be affected.
advisories (2)
Vendor and ecosystem advisories describing this.
- GHSA-p897-vf7j-f5h8BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints2026-06-21ghsa · osvUS
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.
- PYSEC-2026-4074BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints2026-10-01vendor · osvUS
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.
also known as (5)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (16)
External citations — patches, advisories, analysis.
- https://gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817acnnvd
- https://github.com/BerriAI/litellm/releasesPatchcnnvd
- https://vuldb.com/cve/CVE-2026-12797cnnvd
- https://vuldb.com/submit/811288cnnvd
- https://vuldb.com/vuln/372559cnnvd
- https://vuldb.com/vuln/372559/cticnnvd
- https://gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817aenisa_euvd
- https://vuldb.com/cve/CVE-2026-12797enisa_euvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan