Medium Access control exploit reference

CVE-2026-12797 — BerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization

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.

Published Jun 21, 2026 · Updated Oct 13, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: VulDB

Low

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.

How the score was calculated

EPSS 0.4% (30-day exploitation probability)+5
Technical severity (medium)+3
CISA SSVC: exploitation "poc"+5

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation

Not confirmed

Not in CISA KEV — an absence of record, not proof it is unexploited.

EPSS FIRST

0.4%

ahead of 33% of scored CVEs · Oct 14, 2026

Affects

BerriAI

Litellm

CVSS base

6.3

Medium · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation

Proof of concept

none · proof-of-concept · active

Automatable

can an attacker script the kill-chain steps

Technical impact

Partial

partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

Identify exposed assets running the affected vendor/product/version combinations (BerriAI Litellm, Litellm Litellm).
No fix documented in the sources: reduce exposure and monitor the vendor advisory.
Search available logs for exploit probes matching the vulnerability class (access control), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

Vendor	Product	Versions	Status	Source
BerriAI	Litellm	version 1.82.0version 1.82.1version 1.82.2version 1.82.3version 1.82.4version 1.82.5	Vulnerable	CVE Program (cve.org) e CISA ADP
Litellm	Litellm	≤ 1.82.5	Vulnerable	NIST National Vulnerability Database

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector

Network

Attack complexity

Low

Privileges required

Low

User interaction

None

Scope

Unchanged

Confidentiality

Low

Integrity

Low

Availability

Low

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Scored by
5.3	CVSS 4.0	Medium	—	—	VulDB via CVE Program (cve.org) e CISA ADP
2.1	CVSS 4.0	Low	—	—	cna@vuldb.com via NIST National Vulnerability Database
6.3	CVSS 3.1	Medium	2.8	3.4	cna@vuldb.com via NIST National Vulnerability Database
6.3	CVSS 3.1	Medium	—	—	VulDB via CVE Program (cve.org) e CISA ADP
6.3	CVSS 3.0	Medium	—	—	VulDB via CVE Program (cve.org) e CISA ADP
6.5	CVSS 2.0	Medium	8.0	6.4	cna@vuldb.com via NIST National Vulnerability Database
6.5	CVSS 2.0	Medium	—	—	VulDB via CVE Program (cve.org) e CISA ADP

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L (score shown at the top: cna@vuldb.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-285 · Improper Authorization

Other CVEs with this weakness →

EPSS over time FIRST

Oct 13, 2026 → Oct 14, 2026 · 2 reading(s) · max 0.40%

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
Audit administrative actions and access to resources outside each user’s normal pattern.

web/proxy/WAF logsnetwork IDS/IPSauthentication logsapplication logs

Timeline

What happened to this CVE, newest first.

2026
Affected products added · berriai/litellm
Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
SSVC assessment updated
Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
Record published
Oct 13, 2026
CVSS changed · 6.3
Oct 13, 2026 · NIST National Vulnerability Database
Source status changed · → Analyzed
Oct 13, 2026 · NIST National Vulnerability Database
Record created in this database
Oct 13, 2026 · NIST National Vulnerability Database
CVE published
Jun 21, 2026 · VulDB

Source activity

Repeated readings are counted rather than listed.

1× Official description updated · Oct 13, 2026 – Oct 13, 2026

References

5 on the record

vuldb.com/vuln/372559
Third Party Advisory, VDB Entry, vdb-entry, technical-description, NIST National Vulnerability Database
gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817a
Exploit, Third Party Advisory, exploit, NIST National Vulnerability Database
vuldb.com/cve/CVE-2026-12797
Third Party Advisory, VDB Entry, third-party-advisory, NIST National Vulnerability Database
vuldb.com/vuln/372559/cti
Permissions Required, VDB Entry, signature, permissions-required, NIST National Vulnerability Database
vuldb.com/submit/811288
Third Party Advisory, Exploit, VDB Entry, third-party-advisory, NIST National Vulnerability Database

Elsewhere on this site

BerriAI
every CVE for this vendor

Access control
same class

CWE-285
other pages naming this weakness

Related CVEs (same products)

Medium CVE-2026-108575 BerriAI LiteLLM Secret Resolution main.py get_secret improper authorization 4d
Medium CVE-2026-108574 BerriAI LiteLLM Spend Tracking spend_management_endpoints.py ui_view_session_spend_logs authorization 4d
High CVE-2026-93355 LiteLLM Weak JWT Authentication via Email-Based User Lookup 17d
High CVE-2026-89032 BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer 20d
Medium CVE-2026-59823 LiteLLM: Server-side request forgery via the `user_config` request parameter in LiteLLM Proxy 29d
Medium CVE-2026-84377 LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters Sep 2, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

No fixed version, patch or mitigation documented.
No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-12797 is "BerriAI litellm Completions banned_keywords.py async_pre_call_hook authorization", rated Medium. It affects Litellm (BerriAI); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 6.3 describes technical severity. EPSS 0.40% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.