CVE-2026-59822

CRITICALNVD 8.29.0
EchelonGraph scoreHIGH confidence

“▲” beside the score: it is higher than NVD's CVSS score.

Score elevated to 9.0 because this CVE is listed on the CISA Known Exploited Vulnerabilities catalog (added 2026-09-02), indicating real-world exploitation has been confirmed by US federal agencies. NVD baseline CVSS 8.2 retained for reference. The 9.0 is the floor for confirmed exploitation, not an impact rating: this CVE's impact severity (EG Severity) is CVSS 8.2 HIGH under NVD CVSS v3. Confidence: HIGH.

Triggered by: CISA KEV (actively exploited)
Sources: CISA Known Exploited Vulnerabilities catalog, EPSS, NVD CVSS v3
Trending — 3 sources updated this weekExploited in the wild

Also known asEUVD-2026-42359 (ENISA EUVD) · GHSA-7488-6r32-c95q (GitHub Security Advisories)Source: ENISA EUVD

9.0EG
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 or medium mission impact
CISA-KEV: ExploitedEPSS PROB: 0.8%CVSS: 8.2Exploit: No code on recordExposed 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. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.

CVSS v3
8.2
EG Score
9.0CRITICALhigh confidence
EG Risk
92
EG Risk 92/100

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)
Severity82% × 45%
Impact severity (EG Severity): CVSS 8.2 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 or medium mission impact; Act at high (mission-essential systems).
Exploitation active (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 sooner than your standard update timelines at low or medium mission impact and as soon as possible at high.
EPSS PROB
0.8%
EPSS %ILE
57th
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 (9.0): severity, escalated by confirmed exploitation. This CVE's 9.0 is the CISA KEV floor for confirmed exploitation, not an impact rating: its impact severity (EG Severity) is CVSS 8.2 HIGH.

EG Severity
8.2 HIGHCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.NVD CVSS v3 · CVSS v3.0 or v3.1
EG Likelihood
0.8% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-01). 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 Attend at medium mission impactAttend at low or medium mission impact; Act at high (mission-essential systems).CISA BOD 26-04: 3 days if the affected system is publicly exposed; 14 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)Attend at low or medium mission impact; Act at high (mission-essential systems).

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

Exploitation active (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)3 days if the affected system is publicly exposed; 14 days if it is not.

The score's inputs: In CISA KEV yes (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

CISA required action“Apply mitigations in accordance with vendor instructions, ensuring compliance with CISA’s BOD 26-04 Prioritizing Security Updates Based on Risk (see URL in Notes) guidance and CISA’s “Forensics Triage Requirements” (see URL in Notes). Follow applicable BOD 26-04 guidance for cloud services or discontinue use of the product if mitigations are unavailable. Stakeholders are responsible for evaluating each asset's internet exposure and ensuring adherence to BOD 26-04 patching guidelines.”

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-7488-6r32-c95q · https://www.cisa.gov/news-events/directives/bod-26-04-prioritizing-security-updates-based-risk · https://www.cisa.gov/news-events/directives/bod-26-04-implementation-guidance-prioritizing-security-updates-based-risk · https://nvd.nist.gov/vuln/detail/CVE-2026-59822

Published

July 8, 2026

Last Modified

October 25, 2026

Advisory Details (6)

Auto-updated Nov 1, 2026
⚠️ Actively exploited (CISA KEV, CISA Vulnrichment). Patch available. Sources: cisa, github_commit, github_pr, github_release, github.
Web page

Attacks on AI Infrastructure: 90-Day Honeypot Telemetry | Wiz Blog

https://www.wiz.io/blog/ai-infrastructure-honeypot
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-2026-59822
GitHub advisoryMentions a patch (unverified)

MCP Authentication Bypass via OAuth2 Passthrough Fallback · Advisory · BerriAI/litellm · GitHub

https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q
GitHub release Patch Available

v1.84.0

Patch available: BerriAI/litellm v1.84.0

https://github.com/BerriAI/litellm/releases/tag/v1.84.0
GitHub pull request

fix(mcp): tighten public-route detection and OAuth2 fallback gating

Fix merged in BerriAI/litellm PR #26463 on 2026-04-30 — awaiting tagged release

https://github.com/BerriAI/litellm/pull/26463
GitHub commit

commit 73869f0faf7d (BerriAI/litellm)

Fix landed in BerriAI/litellm commit 73869f0faf7d — awaiting tagged release

https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c

Vendor Advisories for CVE-2026-59822(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 (1119 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 16× in last 7d / 63× 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 238 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 138 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-02 16:45 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  2. 2026-11-02 01:37 UTCEG score recompute
  3. 2026-11-02 01:36 UTCGHSA enrichmentGHSA-7488-6r32-c95q · GitHub severity HIGH
  4. 2026-11-01 16:35 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  5. 2026-11-01 07:42 UTCGHSA enrichmentGHSA-7488-6r32-c95q · GitHub severity HIGH
  6. 2026-11-01 03:28 UTCEG score recompute
  7. 2026-10-31 16:33 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  8. 2026-10-31 05:20 UTCEG score recompute
  9. 2026-10-30 16:34 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  10. 2026-10-30 07:12 UTCEG score recompute
  11. 2026-10-29 16:33 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  12. 2026-10-29 09:04 UTCEG score recompute
  13. 2026-10-28 16:32 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  14. 2026-10-28 10:57 UTCEG score recompute
  15. 2026-10-27 16:32 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  16. 2026-10-27 12:49 UTCEG score recompute
  17. 2026-10-26 16:31 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  18. 2026-10-25 17:27 UTCEG score recompute
  19. 2026-10-25 16:33 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  20. 2026-10-25 14:16 UTCEG score recompute
  21. 2026-10-25 12:51 UTCEG score recompute
  22. 2026-10-24 16:33 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  23. 2026-10-23 16:35 UTCEG score recompute
  24. 2026-10-23 16:32 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  25. 2026-10-22 18:24 UTCEG score recompute
Show 75 more
  1. 2026-10-22 16:34 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  2. 2026-10-21 20:16 UTCEG score recompute
  3. 2026-10-21 16:33 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  4. 2026-10-20 22:08 UTCEG score recompute
  5. 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  6. 2026-10-19 23:55 UTCEG score recompute
  7. 2026-10-19 16:32 UTCEPSS rescoreEPSS 0.8% · 57th percentile
  8. 2026-10-19 01:47 UTCEG score recompute
  9. 2026-10-18 16:32 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  10. 2026-10-18 03:27 UTCEG score recompute
  11. 2026-10-17 16:35 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  12. 2026-10-17 05:31 UTCEG score recompute
  13. 2026-10-16 16:43 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  14. 2026-10-16 07:23 UTCEG score recompute
  15. 2026-10-15 16:32 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  16. 2026-10-15 09:16 UTCEG score recompute
  17. 2026-10-14 16:33 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  18. 2026-10-14 11:06 UTCEG score recompute
  19. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  20. 2026-10-13 12:58 UTCEG score recompute
  21. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  22. 2026-10-12 14:49 UTCEG score recompute
  23. 2026-10-11 19:36 UTCEG score recompute
  24. 2026-10-11 16:51 UTCEG score recompute
  25. 2026-10-11 14:13 UTCEG score recompute
  26. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  27. 2026-10-10 21:48 UTCEG score recompute
  28. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  29. 2026-10-09 20:55 UTCEG score recompute
  30. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  31. 2026-10-08 20:02 UTCEG score recompute
  32. 2026-10-08 17:13 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  33. 2026-10-08 03:25 UTCEG score recompute
  34. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  35. 2026-10-06 18:15 UTCEG score recompute
  36. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  37. 2026-10-05 21:30 UTCEG score recompute
  38. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  39. 2026-10-03 15:33 UTCEG score recompute
  40. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  41. 2026-10-02 18:49 UTCEG score recompute
  42. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  43. 2026-10-01 22:04 UTCEG score recompute
  44. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  45. 2026-09-30 16:59 UTCEG score recompute
  46. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  47. 2026-09-29 16:06 UTCEG score recompute
  48. 2026-09-29 15:22 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  49. 2026-09-28 23:30 UTCEG score recompute
  50. 2026-09-28 15:11 UTCEG score recompute
  51. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  52. 2026-09-27 21:51 UTCCISA KEV update
  53. 2026-09-27 14:18 UTCEG score recompute
  54. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  55. 2026-09-26 17:33 UTCEG score recompute
  56. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  57. 2026-09-26 00:56 UTCEG score recompute
  58. 2026-09-25 19:35 UTCCISA KEV update
  59. 2026-09-25 14:55 UTCCISA KEV update
  60. 2026-09-24 19:31 UTCCISA KEV update
  61. 2026-09-24 15:44 UTCEG score recompute
  62. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  63. 2026-09-23 19:01 UTCEG score recompute
  64. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  65. 2026-09-22 19:36 UTCCISA KEV update
  66. 2026-09-22 18:05 UTCEG score recompute
  67. 2026-09-21 21:21 UTCEG score recompute
  68. 2026-09-21 19:09 UTCCISA KEV update
  69. 2026-09-20 20:28 UTCEG score recompute
  70. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  71. 2026-09-19 19:37 UTCEG score recompute
  72. 2026-09-18 22:52 UTCEG score recompute
  73. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  74. 2026-09-18 19:20 UTCCISA KEV update
  75. 2026-09-18 14:15 UTCCISA KEV update

Frequently asked(6)

What is CVE-2026-59822?
CVE-2026-59822 is a critical-severity vulnerability; its CVE record was published on July 8, 2026. LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key…
When was the CVE record for CVE-2026-59822 published?
The CVE record for CVE-2026-59822 was published on July 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 25, 2026; the record at its source may have been updated since.
Is CVE-2026-59822 actively exploited?
Yes. CISA added CVE-2026-59822 to the Known Exploited Vulnerabilities catalog on September 2, 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-2026-59822?
CVE-2026-59822 has a CVSS v3 base score of 8.2 (NVD). EchelonGraph synthesises NVD + CISA KEV + FIRST EPSS into a combined EG score of 9.0 (CRITICAL).
Which products are affected by CVE-2026-59822?
CVE-2026-59822 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-2026-59822?
A fix for CVE-2026-59822 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-59822 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-2026-59822

Explore →

Is Your Infrastructure Affected by CVE-2026-59822?

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