LiveActive security incident?Get immediate response
CVE Record

CVE-2026-42208: LiteLLM: SQL injection in Proxy API key verification

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.

CriticalCVSS 9.8Known exploitedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysiscritical

Security readout for executives and security teams

Plain-English summary

LiteLLM AI Gateway versions 1.81.16 through before 1.83.7 can mishandle API key checks in a way that lets an unauthenticated attacker reach the proxy database. That database may contain access records and managed credentials, so compromise could affect both the gateway and connected AI services.

Executive priority

Treat this as an emergency patch item. It is remotely reachable, unauthenticated, critical severity, and listed in CISA KEV, with potential exposure of credentials managed by the AI gateway.

Technical view

This is CWE-89 SQL injection in LiteLLM proxy API key verification. The key value was mixed into query text instead of parameterized. The issue is reachable through LLM API routes during error handling and can allow database reads and possible modification. Version 1.83.7 contains the patch.

Likely exposure

Exposure is likely where LiteLLM proxy versions >=1.81.16 and <1.83.7 are deployed, especially if LLM API routes are reachable from the internet or broad internal networks.

Exploitation context

CISA KEV listing indicates known exploitation. The provided sources do not include campaign details, exploit volume, targets, or indicators of compromise, so those should not be inferred.

Researcher notes

Focus on asset discovery, version confirmation, reachability of LiteLLM API routes, and database integrity review. Sources support active exploitation through KEV, but do not provide public exploitation details or IOCs in the supplied bundle.

Mitigation direction

  • Upgrade LiteLLM to version 1.83.7 or later immediately.
  • Identify all LiteLLM proxy deployments and confirm their running versions.
  • If upgrade is delayed, check BerriAI guidance for supported temporary controls.
  • Review managed credentials and access records for possible exposure.
  • Follow incident response procedures for credential rotation if compromise is suspected.

Validation and detection

  • Confirm deployed LiteLLM versions are not >=1.81.16 and <1.83.7.
  • Verify the proxy package or container now uses 1.83.7 or later.
  • Review proxy access logs for unusual unauthenticated LLM API requests.
  • Check database audit logs for unexpected reads or writes, if available.
  • Confirm exposed LiteLLM routes are limited to intended trusted clients.
Prepared
Confidence
high
Sources
8

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · medium confidence lookup

CWE-89: Database access and collection lookup

Injection into data stores can inform collection, data access, and exfiltration detection reviews. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
description · low confidence lookup

Database behavior lookup

The CVE wording references database injection or access, so collection and exfiltration review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-42208 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
Critical
CVSS
9.8 (3.1)
Known Exploited
Yes
Published

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

2CVSS vectors
7Timeline events
2ADP providers
7Source links

CISA KEV status

Status
Known exploited
Source
CISA-ADP
Date added
KEV reference

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: activeAutomatable: yesTechnical Impact: total

CVSS vector scores

2 official scores

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
9.8CVSS 3.1CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H3.95.9redhat-SADP
9.3CVSS 4.0CriticalCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N——GitHub_M

Vulnerability scoring details

Base CVSS 4.0 score

9.3Critical
CVSS 4.0 vector shape for CVE-2026-42208Attack VectorAttack ComplexityAttack RequirementsPrivileges RequiredUser InteractionVS ConfidentialityVS IntegrityVS AvailabilitySS ConfidentialitySS IntegritySS Availability

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Attack Requirements
NonePresent
Privileges Required
NoneLowHigh
User Interaction
NonePassiveActive
VS Confidentiality
HighLowNone
VS Integrity
HighLowNone
VS Availability
HighLowNone
SS Confidentiality
HighLowNone
SS Integrity
HighLowNone
SS Availability
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. ADP timelineredhat-SADP

    Reported to Red Hat.

  4. Added to KEVCISA-ADP

    CISA Known Exploited Vulnerabilities metadata lists this CVE as known exploited.

  5. ADP timelineCISA-ADP

    CVE-2026-42208 added to CISA KEV

  6. CVE publishedCVE Program

    The CVE record was published.

  7. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvcother:kev
  • 2026-05-08T00:00:00.000Z: CVE-2026-42208 added to CISA KEV
redhat-SADPLiteLLM: LiteLLM: Unauthorized data access and modification via SQL injection
other:Red Hat severity ratingcvssV3_1
  • 2026-04-29T22:15:41.713Z: Reported to Red Hat.
  • 2026-04-28T00:00:00.000Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
BerriAIlitellm>= 1.81.16, < 1.83.7Listed
Weakness

CWE details

CWE-89

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.

CWE-89 · source CWE mapping

Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection')

Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs