CVE-2026-42208

CRITICALNVD 9.89.8
EchelonGraph scoreHIGH confidence

“—” beside the score: it is equal to NVD's CVSS score.

Score elevated to 9.8 because this CVE is listed on the CISA Known Exploited Vulnerabilities catalog (added 2026-05-08), indicating real-world exploitation has been confirmed by US federal agencies. NVD baseline CVSS 9.8 retained for reference. Confidence: HIGH.

Triggered by: CISA KEV (actively exploited)
Sources: CISA Known Exploited Vulnerabilities catalog, EPSS, GitHub Security Advisory, NVD CVSS v3
Exploited in the wild

Also known asEUVD-2026-28503 (ENISA EUVD) · GHSA-r75f-5x8p-qvmc (GitHub Security Advisories) · PYSEC-2026-391 (OSV.dev)Source: ENISA EUVD

9.8EG
EchelonGraph verdictPatch nowTreat as an emergency — this is being exploited.
  • Actively exploited in the wild (CISA-KEV) — the reason this is sooner than the SSVC decision on this page at low mission impact
CISA-KEV: ExploitedEPSS PROB: 89%CVSS: 9.8Exploit: MetasploitExposed services: Not assessed

A fix is available — apply it.

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.

CVSS v3
9.8
EG Score
9.8CRITICALhigh confidence
EG Risk
99
EG Risk 99/100

EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.

How it’s computed (value × EchelonGraph’s weight)
Severity98% × 45%
Impact severity (EG Severity): CVSS 9.8 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation100% × 40%
Fixed at 100% for a CISA KEV listing: EchelonGraph's rule.
Automatability100% × 15%
CISA's SSVC Automatable value: yes (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Attend at low mission impact; Act at medium or high.
Exploitation active (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: A fix is available. Apply it sooner than your standard update timelines at low mission impact and as soon as possible at medium or high.
EPSS PROB
89%
EPSS %ILE
99th
KEV
⚠ Exploited

What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)

The EG score (9.8): severity, escalated by confirmed exploitation. This CVE's 9.8 is its impact severity (EG Severity), not escalated.

EG Severity
9.8 CRITICALCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
EG Likelihood
89% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-12). FIRST's exploitation probability, not an EchelonGraph model.
Confirmed exploitation
CISA KEV and EG-KEV Tier 1 (exploited in the wild)Reported apart from the likelihood: an observed fact, not a probability.
EG Priority
SSVC Act at medium mission impactAttend at low mission impact; Act at medium or high.CISA BOD 26-04: 3 days & forensic triage if the affected system is publicly exposed; 3 days & forensic triage if it is not.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.

SSVC (CISA's decision table, applied by EchelonGraph)Attend at low mission impact; Act at medium or high.

A fix is available. Apply it sooner than your standard update timelines at low mission impact and as soon as possible at medium or high.

Exploitation active (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table

BOD 26-04 (CISA's remediation timeline, Table 1)3 days & forensic triage if the affected system is publicly exposed; 3 days & forensic triage if it is not.

The score's inputs: In CISA KEV yes (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it

CISA required action“Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.”

Quoted verbatim from CISA's Known Exploited Vulnerabilities catalog. CISA directs it at US federal civilian executive branch agencies under Binding Operational Directive (BOD) 26-04, which replaced BOD 22-01 on 10 June 2026; it is not EchelonGraph's advice. CISA's notes: https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc · https://nvd.nist.gov/vuln/detail/CVE-2026-42208

Published

May 8, 2026

Last Modified

October 26, 2026

Advisory Details (6)

Auto-updated Nov 10, 2026
⚠️ Actively exploited (CISA KEV, CISA Vulnrichment). Patch available. Sources: cisa, github, github_release, redhat.
CISA🔴 Active Exploitation

Known Exploited Vulnerabilities Catalog | CISA

Known Exploited Vulnerabilities Catalog | CISA. Listed in CISA Known Exploited Vulnerabilities catalog.

https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-42208
Red Hat

2463965 – (CVE-2026-42208) CVE-2026-42208 LiteLLM: LiteLLM: Unauthorized data access and modification via SQL injection

https://bugzilla.redhat.com/show_bug.cgi?id=2463965
Red HatMentions a patch (unverified)

CVE-2026-42208 - Red Hat Customer Portal

Affected: Red Hat Enterprise Linux 8 or OpenShift Container Platform 4, is affected by this vulnerability and a fix may be released to a

https://access.redhat.com/security/cve/CVE-2026-42208
GitHub advisoryMentions a patch (unverified)

SQL injection in Proxy API key verification · Advisory · BerriAI/litellm · GitHub

https://github.com/BerriAI/litellm/security/advisories/GHSA-r75f-5x8p-qvmc
GitHub release Patch Available

v1.83.7-stable

Patch available: BerriAI/litellm v1.83.7-stable

https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable

Vendor Advisories for CVE-2026-42208(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Patch Availability(1)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
piplitellm @ 1.83.7 (fixes >= 1.81.16, < 1.83.7)—ghsa

Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
litellm1.81.16 ... 1.83.6 (15 versions)
  • 1.81.16 up to 1.83.7: fixed in 1.83.7
—

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 9× in last 7d / 32× in last 30d)

Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed its CVE.org record (CNA or CISA ADP). An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). "EchelonGraph re-scored" is our own recompute of this CVE's score, not an update from a source, and is not counted in the refreshes above. Most recent first.

Showing the most recent 100 of 271 rows on record for this CVE.

A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. None are among the latest 100 rows. The 171 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-13 16:52 UTCEPSS rescoreEPSS 89% · 99th percentile
  2. 2026-11-13 01:33 UTCEchelonGraph re-scored
  3. 2026-11-13 01:33 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  4. 2026-11-12 02:13 UTCEchelonGraph re-scored
  5. 2026-11-12 02:13 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  6. 2026-11-11 16:39 UTCEPSS rescoreEPSS 89% · 99th percentile
  7. 2026-11-11 02:54 UTCEchelonGraph re-scored
  8. 2026-11-11 02:54 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  9. 2026-11-10 03:34 UTCEchelonGraph re-scored
  10. 2026-11-10 03:34 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  11. 2026-11-09 04:15 UTCEchelonGraph re-scored
  12. 2026-11-09 04:15 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  13. 2026-11-08 04:49 UTCEchelonGraph re-scored
  14. 2026-11-08 04:49 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  15. 2026-11-07 05:29 UTCEchelonGraph re-scored
  16. 2026-11-07 05:29 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  17. 2026-11-06 16:37 UTCEPSS rescoreEPSS 89% · 99th percentile
  18. 2026-11-06 08:25 UTCOSV refresh
  19. 2026-11-06 06:09 UTCEchelonGraph re-scored
  20. 2026-11-06 06:09 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  21. 2026-11-05 06:50 UTCEchelonGraph re-scored
  22. 2026-11-05 06:50 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  23. 2026-11-04 16:35 UTCEPSS rescoreEPSS 89% · 99th percentile
  24. 2026-11-04 07:30 UTCEchelonGraph re-scored
  25. 2026-11-04 07:30 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
Show 75 more
  1. 2026-11-03 16:48 UTCEPSS rescoreEPSS 89% · 99th percentile
  2. 2026-11-03 08:10 UTCEchelonGraph re-scored
  3. 2026-11-03 08:10 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  4. 2026-11-02 08:50 UTCEchelonGraph re-scored
  5. 2026-11-02 08:50 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  6. 2026-11-01 09:31 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  7. 2026-11-01 07:50 UTCGHSA enrichmentGHSA-r75f-5x8p-qvmc · GitHub severity CRITICAL · GitHub CVSS 9.8
  8. 2026-11-01 07:50 UTCEchelonGraph re-scored
  9. 2026-10-31 10:12 UTCEchelonGraph re-scored
  10. 2026-10-30 16:34 UTCEPSS rescoreEPSS 89% · 99th percentile
  11. 2026-10-30 10:47 UTCEchelonGraph re-scored
  12. 2026-10-29 11:27 UTCEchelonGraph re-scored
  13. 2026-10-28 16:32 UTCEPSS rescoreEPSS 89% · 99th percentile
  14. 2026-10-28 12:08 UTCEchelonGraph re-scored
  15. 2026-10-26 20:27 UTCEchelonGraph re-scored
  16. 2026-10-26 05:37 UTCEchelonGraph re-scored
  17. 2026-10-25 16:33 UTCEPSS rescoreEPSS 89% · 99th percentile
  18. 2026-10-25 14:29 UTCEchelonGraph re-scored
  19. 2026-10-25 06:17 UTCEchelonGraph re-scored
  20. 2026-10-24 16:33 UTCEPSS rescoreEPSS 5.8% · 93rd percentile
  21. 2026-10-24 06:57 UTCEchelonGraph re-scored
  22. 2026-10-23 16:31 UTCEPSS rescoreEPSS 5.8% · 93rd percentile
  23. 2026-10-23 07:37 UTCEchelonGraph re-scored
  24. 2026-10-22 16:34 UTCEPSS rescoreEPSS 5.8% · 93rd percentile
  25. 2026-10-22 08:17 UTCEchelonGraph re-scored
  26. 2026-10-21 16:33 UTCEPSS rescoreEPSS 5.8% · 93rd percentile
  27. 2026-10-21 08:57 UTCEchelonGraph re-scored
  28. 2026-10-20 16:33 UTCEPSS rescoreEPSS 5.8% · 93rd percentile
  29. 2026-10-20 09:37 UTCEchelonGraph re-scored
  30. 2026-10-19 16:32 UTCEPSS rescoreEPSS 5.8% · 93rd percentile
  31. 2026-10-19 10:16 UTCEchelonGraph re-scored
  32. 2026-10-18 03:41 UTCEchelonGraph re-scored
  33. 2026-10-17 16:34 UTCEPSS rescoreEPSS 5.8% · 93rd percentile
  34. 2026-10-17 11:35 UTCEchelonGraph re-scored
  35. 2026-10-16 16:42 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  36. 2026-10-16 12:14 UTCEchelonGraph re-scored
  37. 2026-10-15 16:32 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  38. 2026-10-15 12:53 UTCEchelonGraph re-scored
  39. 2026-10-14 16:33 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  40. 2026-10-14 13:31 UTCEchelonGraph re-scored
  41. 2026-10-13 16:34 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  42. 2026-10-13 14:11 UTCEchelonGraph re-scored
  43. 2026-10-12 16:34 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  44. 2026-10-12 14:49 UTCEchelonGraph re-scored
  45. 2026-10-11 19:49 UTCEchelonGraph re-scored
  46. 2026-10-11 17:03 UTCEchelonGraph re-scored
  47. 2026-10-11 14:29 UTCEchelonGraph re-scored
  48. 2026-10-11 13:48 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  49. 2026-10-11 11:40 UTCEchelonGraph re-scored
  50. 2026-10-10 22:45 UTCEchelonGraph re-scored
  51. 2026-10-10 20:00 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  52. 2026-10-09 20:55 UTCEchelonGraph re-scored
  53. 2026-10-09 20:07 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  54. 2026-10-08 19:08 UTCEchelonGraph re-scored
  55. 2026-10-08 17:12 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  56. 2026-10-08 01:54 UTCEchelonGraph re-scored
  57. 2026-10-07 23:48 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  58. 2026-10-06 15:32 UTCEchelonGraph re-scored
  59. 2026-10-06 15:17 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  60. 2026-10-05 18:02 UTCEchelonGraph re-scored
  61. 2026-10-05 17:43 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  62. 2026-10-03 18:43 UTCEchelonGraph re-scored
  63. 2026-10-03 14:25 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  64. 2026-10-02 16:49 UTCEchelonGraph re-scored
  65. 2026-10-01 23:36 UTCEchelonGraph re-scored
  66. 2026-10-01 19:50 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  67. 2026-09-30 17:29 UTCEchelonGraph re-scored
  68. 2026-09-30 15:03 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  69. 2026-09-29 15:41 UTCEchelonGraph re-scored
  70. 2026-09-28 22:30 UTCEchelonGraph re-scored
  71. 2026-09-28 13:55 UTCEchelonGraph re-scored
  72. 2026-09-27 21:51 UTCCISA KEV update
  73. 2026-09-27 16:26 UTCEchelonGraph re-scored
  74. 2026-09-27 13:48 UTCEPSS rescoreEPSS 5.8% · 92nd percentile
  75. 2026-09-26 18:52 UTCEchelonGraph re-scored

Publicly available exploits

(2 references)

Public exploit code is referenced for this CVE (1 Metasploit module), as is 1 Nuclei detection template. A detection template checks whether a system is affected; it is not necessarily exploit code. Defenders should treat patch urgency accordingly.

  • Metasploitauxiliary/scanner/http/litellm_proxy_sqli✓ verified
    Published Jun 23, 2026

    BerriAI LiteLLM Proxy Pre-Auth SQL Injection Scanner

    Open source ↗
  • Nucleihttp/cves/2026/CVE-2026-42208.yaml
    Published Jun 1, 2026

    LiteLLM - SQL Injection

    Open source ↗

Frequently asked(6)

What is CVE-2026-42208?
CVE-2026-42208 is a critical-severity vulnerability; its CVE record was published on May 8, 2026. 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…
When was the CVE record for CVE-2026-42208 published?
The CVE record for CVE-2026-42208 was published on May 8, 2026. That is the record's publication date; the vulnerability itself may have been made public earlier. EchelonGraph's copy of the record carries a last-modified date of October 26, 2026; the record at its source may have been updated since.
Is CVE-2026-42208 actively exploited?
Yes. CISA added CVE-2026-42208 to the Known Exploited Vulnerabilities catalog on May 8, 2026, affecting BerriAI LiteLLM. KEV listing indicates confirmed exploitation in the wild; this CVE warrants immediate attention. A fix is available. Apply it.
What is the CVSS score of CVE-2026-42208?
CVE-2026-42208 has a CVSS v3 base score of 9.8 (NVD).
Which products are affected by CVE-2026-42208?
CVE-2026-42208 affects BerriAI LiteLLM. The affected packages EchelonGraph has on record, with version ranges, are listed in the Affected Packages section of this page.
How do I remediate CVE-2026-42208?
A fix for CVE-2026-42208 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-42208 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-42208

Explore →

Is Your Infrastructure Affected by CVE-2026-42208?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.