CVE-2026-12773

CRITICALNVD 9.89.8
EchelonGraph scoreMEDIUM confidence

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

This critical-severity CVE scores 9.8 under NVD CVSS v3. EPSS exploit probability: 1.0% (63rd percentile of EPSS-scored CVEs). GitHub Security Advisory CVSS 7.3 is lower than this score; a lower GitHub score revises it only when its advisory is newer than the CVE record's last change, and this advisory (published 2026-06-21) is not newer than that change (2026-10-25), so it does not.

Triggered by: Headline CVSS from NVD CVSS v3
Sources: EPSS, GitHub Security Advisory, NVD CVSS v3
Trending — 3 sources updated this weekElevated

Also known asEUVD-2026-38139 (ENISA EUVD) · GHSA-4jcj-7x88-m979 (GitHub Security Advisories)Source: ENISA EUVD

9.8EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (the SSVC decision on this page).
  • CISA's Vulnrichment rates exploitation as PoC; EchelonGraph holds no exploit-code reference for it
CISA-KEV: Not listedEPSS PROB: 1.0%CVSS: 9.8Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

A weakness has been identified in BerriAI litellm up to 1.59.8. Affected is the function UserAPIKeyAuth of the file litellm/proxy/_experimental/mcp_server/auth/user_api_key_auth_mcp.py of the component MCP Proxy. Executing a manipulation can lead to improper authentication. The attack may be launched remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure.

CVSS v3
9.8
EG Score
9.8CRITICALmedium confidence
EG Risk
75
EG Risk 75/100

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.
Exploitation40% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 3 (Elevated): a constant, not a probability.
Automatability100% × 15%
CISA's SSVC Automatable value: yes (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Attend at high (mission-essential systems).
Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (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 within your standard update timelines at low or medium mission impact and sooner than that at high.
EPSS PROB
1.0%
EPSS %ILE
63rd
KEV
Not listed

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.NVD CVSS v3 · CVSS v3.0 or v3.1
EG Likelihood
1.0% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-01). FIRST's exploitation probability, not an EchelonGraph model.
Confirmed exploitation
None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
EG Priority
SSVC Track at medium mission impactTrack at low or medium mission impact; Attend at high (mission-essential systems).CISA BOD 26-04: 14 days if the affected system is publicly exposed; 60 days 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)Track at low or medium mission impact; Attend at high (mission-essential systems).

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

Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (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)14 days if the affected system is publicly exposed; 60 days if it is not.

The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact partial (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

Published

June 21, 2026

Last Modified

October 25, 2026

Advisory Details (4)

Auto-updated Nov 2, 2026
Patch available. Sources: redhat.
Red Hat

2491112 – (CVE-2026-12773) CVE-2026-12773 litellm: BerriAI litellm: Improper authentication in MCP Proxy via UserAPIKeyAuth function

https://bugzilla.redhat.com/show_bug.cgi?id=2491112
Red HatMentions a patch (unverified)

CVE-2026-12773 - 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-2026-12773
Web page

Critical Authentication Bypass and Privilege Escalation via Exception Swallowing in MCP Proxy · GitHub

https://gist.github.com/YLChen-007/3cfaad10a69d7a15e4d4d458cb53309e

Vendor Advisories for CVE-2026-12773(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 @ 1.84.0 (fixes < 1.84.0)—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
litellm0.1.0 ... 1.9.dev0 (745 versions)
  • every version up to 1.84.0: fixed in 1.84.0
—

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 15× in last 7d / 58× 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 it from the CNA feed. 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). Most recent first.

Showing the most recent 100 of 370 refreshes 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 270 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-02 04:55 UTCEG score recompute
  2. 2026-11-02 04:55 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub severity MODERATE · GitHub CVSS 7.3
  3. 2026-11-01 16:34 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  4. 2026-11-01 06:17 UTCEG score recompute
  5. 2026-10-31 16:32 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  6. 2026-10-31 07:38 UTCEG score recompute
  7. 2026-10-30 16:33 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  8. 2026-10-30 09:00 UTCEG score recompute
  9. 2026-10-29 16:32 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  10. 2026-10-29 10:22 UTCEG score recompute
  11. 2026-10-28 16:31 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  12. 2026-10-28 11:44 UTCEG score recompute
  13. 2026-10-27 16:31 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  14. 2026-10-27 02:07 UTCEG score recompute
  15. 2026-10-26 16:30 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  16. 2026-10-25 23:26 UTCEG score recompute
  17. 2026-10-25 23:26 UTCNVD updateCVSS v4 → 5.5
  18. 2026-10-25 16:32 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  19. 2026-10-25 14:49 UTCEG score recompute
  20. 2026-10-25 01:00 UTCEG score recompute
  21. 2026-10-24 16:32 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  22. 2026-10-24 02:22 UTCEG score recompute
  23. 2026-10-23 16:31 UTCEPSS rescoreEPSS 1.0% · 63rd percentile
  24. 2026-10-23 03:42 UTCEG score recompute
  25. 2026-10-22 16:33 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
Show 75 more
  1. 2026-10-22 04:59 UTCEG score recompute
  2. 2026-10-21 16:32 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  3. 2026-10-21 06:18 UTCEG score recompute
  4. 2026-10-20 16:32 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  5. 2026-10-20 07:40 UTCEG score recompute
  6. 2026-10-19 16:31 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  7. 2026-10-19 08:59 UTCEG score recompute
  8. 2026-10-18 16:31 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  9. 2026-10-18 05:04 UTCEG score recompute
  10. 2026-10-17 16:33 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  11. 2026-10-17 06:44 UTCEG score recompute
  12. 2026-10-16 16:40 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  13. 2026-10-16 08:02 UTCEG score recompute
  14. 2026-10-15 16:31 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  15. 2026-10-15 07:04 UTCEG score recompute
  16. 2026-10-14 16:32 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  17. 2026-10-14 02:53 UTCEG score recompute
  18. 2026-10-13 16:33 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  19. 2026-10-12 16:36 UTCEG score recompute
  20. 2026-10-12 16:33 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  21. 2026-10-11 20:12 UTCEG score recompute
  22. 2026-10-11 18:24 UTCEG score recompute
  23. 2026-10-11 14:57 UTCEG score recompute
  24. 2026-10-11 13:48 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  25. 2026-10-10 19:59 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  26. 2026-10-09 20:06 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  27. 2026-10-08 17:11 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  28. 2026-10-07 23:47 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  29. 2026-10-06 15:17 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  30. 2026-10-05 17:42 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  31. 2026-10-04 23:21 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  32. 2026-10-03 14:49 UTCOSV refresh
  33. 2026-10-03 14:25 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  34. 2026-10-01 19:49 UTCEPSS rescoreEPSS 1.0% · 62nd percentile
  35. 2026-09-30 15:02 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  36. 2026-09-29 15:20 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  37. 2026-09-28 13:50 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  38. 2026-09-26 15:58 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  39. 2026-09-23 13:47 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  40. 2026-09-20 20:15 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  41. 2026-09-18 19:27 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  42. 2026-09-16 05:14 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  43. 2026-09-14 02:11 UTCEG score recompute
  44. 2026-09-13 16:46 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  45. 2026-09-13 12:53 UTCEG score recompute
  46. 2026-09-12 15:00 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  47. 2026-09-11 14:52 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  48. 2026-09-11 09:36 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  49. 2026-09-10 09:34 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  50. 2026-09-08 22:00 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  51. 2026-09-07 16:01 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  52. 2026-09-06 13:47 UTCEPSS rescoreEPSS 1.0% · 61st percentile
  53. 2026-09-04 05:06 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  54. 2026-09-02 14:11 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  55. 2026-09-01 13:53 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  56. 2026-09-01 04:39 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  57. 2026-08-31 01:01 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  58. 2026-08-30 20:43 UTCEG score recompute
  59. 2026-08-30 20:43 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  60. 2026-08-30 19:17 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  61. 2026-08-30 01:21 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  62. 2026-08-28 21:40 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  63. 2026-08-27 14:24 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  64. 2026-08-25 13:48 UTCEPSS rescoreEPSS 1.0% · 60th percentile
  65. 2026-08-25 06:55 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  66. 2026-08-25 02:37 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  67. 2026-08-24 22:16 UTCEG score recompute
  68. 2026-08-24 22:16 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  69. 2026-08-24 13:57 UTCEG score recompute
  70. 2026-08-24 13:57 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  71. 2026-08-24 06:49 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  72. 2026-08-24 01:08 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  73. 2026-08-23 20:46 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  74. 2026-08-23 16:28 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3
  75. 2026-08-23 12:11 UTCGHSA enrichmentGHSA-4jcj-7x88-m979 · GitHub CVSS 7.3

Frequently asked(5)

What is CVE-2026-12773?
CVE-2026-12773 is a critical-severity vulnerability; its CVE record was published on June 21, 2026. A weakness has been identified in BerriAI litellm up to 1.59.8. Affected is the function UserAPIKeyAuth of the file litellm/proxy/_experimental/mcp_server/auth/user_api_key_auth_mcp.py of the component MCP Proxy. Executing a manipulation can lead to improper authentication. The attack may be…
When was the CVE record for CVE-2026-12773 published?
The CVE record for CVE-2026-12773 was published on June 21, 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 25, 2026; the record at its source may have been updated since.
Is CVE-2026-12773 actively exploited?
CVE-2026-12773 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 1.0% probability of exploitation in the next 30 days (63rd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-12773?
CVE-2026-12773 has a CVSS v3 base score of 9.8 (NVD).
How do I remediate CVE-2026-12773?
A fix for CVE-2026-12773 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-12773 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-2026-12773

Explore →

Is Your Infrastructure Affected by CVE-2026-12773?

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