CVE-2026-59821

HIGHNVD 7.27.2
EchelonGraph scoreMEDIUM confidence

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

This high-severity CVE scores 7.2 under NVD CVSS v3. EPSS exploit probability: 0.9% (58th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from NVD CVSS v3
Sources: EPSS, NVD CVSS v3
7.2EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines (the SSVC decision on this page).
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0.9%CVSS: 7.2Exploit: None knownExposed 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 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable.

CVSS v3
7.2
EG Score
7.2HIGHmedium confidence
EG Risk
33
EG Risk 33/100

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed (value × EchelonGraph’s weight)
Severity72% × 45%
The EG Score, 7.2 of 10.
Exploitation0.9% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at every mission impact level.
Exploitation none (CISA Vulnrichment) · Automatable no (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.
EPSS PROB
0.9%
EPSS %ILE
58th
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at every mission impact level.

A fix is available. Apply it within your standard update timelines.

Exploitation none (CISA Vulnrichment) · Automatable no (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)60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable no (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

July 8, 2026

Last Modified

July 13, 2026

Advisory Details (3)

Auto-updated Jul 13, 2026
Patch available. Sources: github_release, github, github_commit.
GitHub advisoryMentions a patch (unverified)

Custom Code Guardrails production endpoints bypass code safety checks · Advisory · BerriAI/litellm · GitHub

https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278
GitHub release Patch Available

v1.82.0-stable

Patch available: BerriAI/litellm v1.82.0-stable

https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable
GitHub commit

commit e50b4486d0f7 (BerriAI/litellm)

Fix landed in BerriAI/litellm commit e50b4486d0f7 — awaiting tagged release

https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba

Vendor Advisories for CVE-2026-59821(1)

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

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
litellm0.1.0 ... 1.9.dev0 (1094 versions)
  • every version up to 1.82.0: fixed in 1.82.0
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 12× in last 7d / 36× 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 152 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 52 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  2. 2026-10-13 15:51 UTCEG score recompute
  3. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  4. 2026-10-12 15:52 UTCEG score recompute
  5. 2026-10-11 19:36 UTCEG score recompute
  6. 2026-10-11 16:51 UTCEG score recompute
  7. 2026-10-11 14:13 UTCEG score recompute
  8. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  9. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  10. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  11. 2026-10-08 17:13 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  12. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  13. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  14. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  15. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  16. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  17. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  18. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  19. 2026-10-01 16:11 UTCEG score recompute
  20. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  21. 2026-09-29 15:22 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  22. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  23. 2026-09-28 13:22 UTCEG score recompute
  24. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  25. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.9% · 58th percentile
Show 75 more
  1. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  2. 2026-09-24 11:48 UTCEG score recompute
  3. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  4. 2026-09-23 06:10 UTCEG score recompute
  5. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  6. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  7. 2026-09-18 05:43 UTCEG score recompute
  8. 2026-09-17 19:31 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  9. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  10. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  11. 2026-09-15 03:11 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  12. 2026-09-13 23:49 UTCEG score recompute
  13. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  14. 2026-09-12 15:22 UTCEG score recompute
  15. 2026-09-12 03:32 UTCEG score recompute
  16. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  17. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  18. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  19. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  20. 2026-09-06 14:03 UTCEG score recompute
  21. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  22. 2026-09-05 22:47 UTCEG score recompute
  23. 2026-09-04 05:07 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  24. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  25. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  26. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  27. 2026-08-30 19:19 UTCEG score recompute
  28. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  29. 2026-08-30 07:30 UTCEG score recompute
  30. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  31. 2026-08-28 21:42 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  32. 2026-08-27 21:50 UTCEG score recompute
  33. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  34. 2026-08-27 01:29 UTCEG score recompute
  35. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  36. 2026-08-26 08:23 UTCEG score recompute
  37. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.7% · 48th percentile
  38. 2026-08-24 20:33 UTCEG score recompute
  39. 2026-08-23 05:27 UTCEG score recompute
  40. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  41. 2026-08-22 03:46 UTCEG score recompute
  42. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  43. 2026-08-21 03:59 UTCEG score recompute
  44. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  45. 2026-08-20 01:59 UTCEG score recompute
  46. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  47. 2026-08-18 23:22 UTCEG score recompute
  48. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  49. 2026-08-17 23:31 UTCEG score recompute
  50. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  51. 2026-08-16 23:48 UTCEG score recompute
  52. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  53. 2026-08-16 11:59 UTCEG score recompute
  54. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  55. 2026-08-15 12:22 UTCEG score recompute
  56. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  57. 2026-08-14 00:56 UTCEG score recompute
  58. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  59. 2026-08-13 01:18 UTCEG score recompute
  60. 2026-08-12 13:51 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  61. 2026-08-11 13:50 UTCEG score recompute
  62. 2026-08-11 02:01 UTCEG score recompute
  63. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  64. 2026-08-09 14:35 UTCEG score recompute
  65. 2026-08-09 13:46 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  66. 2026-08-09 02:47 UTCEG score recompute
  67. 2026-08-08 16:37 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  68. 2026-08-08 03:10 UTCEG score recompute
  69. 2026-08-06 15:43 UTCEG score recompute
  70. 2026-08-06 13:47 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  71. 2026-08-06 03:41 UTCEG score recompute
  72. 2026-08-05 19:17 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  73. 2026-08-05 01:29 UTCEG score recompute
  74. 2026-08-04 15:10 UTCEPSS rescoreEPSS 0.4% · 28th percentile
  75. 2026-08-04 13:41 UTCEG score recompute

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-59821?
CVE-2026-59821 is a high-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 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to…
When was the CVE record for CVE-2026-59821 published?
The CVE record for CVE-2026-59821 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 July 13, 2026; the record at its source may have been updated since.
Is CVE-2026-59821 actively exploited?
CVE-2026-59821 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.9% probability of exploitation in the next 30 days (58th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-59821?
CVE-2026-59821 has a CVSS v3 base score of 7.2 (NVD).
How do I remediate CVE-2026-59821?
A fix for CVE-2026-59821 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-59821 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-2026-59821

Explore →

Is Your Infrastructure Affected by CVE-2026-59821?

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

Book a Demo →Browse All CVEs