CVE-2026-47101

HIGHPre-NVD 8.88.8
EchelonGraph scoreMEDIUM confidence

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

Score 8.8 from GitHub Security Advisory (severity: HIGH) published 2026-05-21. A secondary CVSS source baseline 8.8; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, a secondary CVSS source
Elevated

Also known asEUVD-2026-31346 (ENISA EUVD) · GHSA-qrc4-49gv-mv9m (GitHub Security Advisories)Source: ENISA EUVD

8.8EG
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: 1.2%CVSS: 8.8Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit. When generating a key, the allowed_routes field is stored without verifying that the specified routes fall within the user's own permissions. A key created with access to admin-only routes can then be used to reach those routes successfully, bypassing the role-based access controls that would otherwise block the request, enabling full privilege escalation from internal_user to proxy_admin.

CVSS v3
8.8
EG Score
8.8HIGHmedium confidence
EG Risk
56
EG Risk 56/100

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)
Severity88% × 45%
Impact severity (EG Severity): CVSS 8.8 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.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low, Track* at medium and Attend at high mission impact.
Exploitation public PoC (CISA Vulnrichment) · Automatable no (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 within your standard update timelines at low or medium mission impact and sooner than that at high.
EPSS PROB
1.2%
EPSS %ILE
67th
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 (8.8): severity, escalated by confirmed exploitation. This CVE's 8.8 is its impact severity (EG Severity), not escalated.

EG Severity
8.8 HIGHCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
EG Likelihood
1.2% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-30). 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, Track* at medium and Attend at high mission impact.CISA BOD 26-04: 14 days if the affected system is publicly exposed; Fix on system upgrade 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, Track* at medium and Attend at high mission impact.

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 no (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)14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable no (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

Published

May 21, 2026

Last Modified

October 8, 2026

Advisory Details (7)

Auto-updated May 22, 2026
Patch available.
Web page

LiteLLM < 1.83.14 Privilege Escalation via API Key Generation | Advisories | VulnCheck

https://www.vulncheck.com/advisories/litellm-privilege-escalation-via-api-key-generation
Web page

huntr - The world’s first bug bounty platform for AI/ML

https://huntr.com/bounties/8e75edfb-ff05-4e63-bfca-2d93d03fb3b9
Web page

Release v1.83.14-stable · BerriAI/litellm · GitHub

https://github.com/BerriAI/litellm/releases/tag/v1.83.14-stable
Web page

fix(proxy): improve input validation on management endpoints · BerriAI/litellm@d910a95 · GitHub

https://github.com/BerriAI/litellm/commit/d910a95661fce3cdd36f3b06c03ecf9c46c6457c
Web page

fix: extend caller-permission checks to service-account + harden raw-… · BerriAI/litellm@5190bd0 · GitHub

https://github.com/BerriAI/litellm/commit/5190bd07eb23a037745d86328096f54378f1614a
Web page

fix: tighten caller-permission checks on key route fields · BerriAI/litellm@2220f30 · GitHub

https://github.com/BerriAI/litellm/commit/2220f3076ac89bd2a2e3439acf57dcfbec2434c9
Web page

LiteLLM-Privilege-Escalation.md · GitHub

https://gist.github.com/13ph03nix/9ec616e1fdc77b3673509c60206e827f

Vendor Advisories for CVE-2026-47101(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 (1115 versions)
  • every version up to 1.83.14: fixed in 1.83.14
—

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 8× in last 7d / 41× 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 236 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 136 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-01 16:34 UTCEPSS rescoreEPSS 1.2% · 67th percentile
  2. 2026-10-31 16:32 UTCEPSS rescoreEPSS 1.2% · 67th percentile
  3. 2026-10-31 04:31 UTCEG score recompute
  4. 2026-10-30 16:34 UTCEPSS rescoreEPSS 1.2% · 67th percentile
  5. 2026-10-29 16:33 UTCEPSS rescoreEPSS 1.2% · 67th percentile
  6. 2026-10-28 16:32 UTCEPSS rescoreEPSS 1.2% · 67th percentile
  7. 2026-10-27 16:32 UTCEPSS rescoreEPSS 1.2% · 67th percentile
  8. 2026-10-26 16:31 UTCEPSS rescoreEPSS 1.2% · 67th percentile
  9. 2026-10-25 16:33 UTCEPSS rescoreEPSS 1.2% · 67th percentile
  10. 2026-10-25 14:24 UTCEG score recompute
  11. 2026-10-24 16:33 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  12. 2026-10-24 08:44 UTCEG score recompute
  13. 2026-10-23 16:31 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  14. 2026-10-22 16:34 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  15. 2026-10-21 16:33 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  16. 2026-10-20 16:33 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  17. 2026-10-19 16:32 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  18. 2026-10-18 16:32 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  19. 2026-10-18 03:36 UTCEG score recompute
  20. 2026-10-17 16:34 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  21. 2026-10-17 12:56 UTCEG score recompute
  22. 2026-10-16 16:42 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  23. 2026-10-15 16:32 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  24. 2026-10-14 16:33 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  25. 2026-10-13 16:34 UTCEPSS rescoreEPSS 1.3% · 70th percentile
Show 75 more
  1. 2026-10-12 16:34 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  2. 2026-10-12 16:02 UTCEG score recompute
  3. 2026-10-11 19:45 UTCEG score recompute
  4. 2026-10-11 16:59 UTCEG score recompute
  5. 2026-10-11 14:24 UTCEG score recompute
  6. 2026-10-11 13:48 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  7. 2026-10-10 20:00 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  8. 2026-10-09 20:07 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  9. 2026-10-08 17:12 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  10. 2026-10-08 16:41 UTCEG score recompute
  11. 2026-10-08 15:47 UTCEG score recompute
  12. 2026-10-07 23:48 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  13. 2026-10-06 15:18 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  14. 2026-10-05 17:43 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  15. 2026-10-04 23:22 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  16. 2026-10-03 14:25 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  17. 2026-10-01 19:50 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  18. 2026-09-30 15:03 UTCEPSS rescoreEPSS 1.3% · 70th percentile
  19. 2026-09-30 02:40 UTCOSV refresh
  20. 2026-09-28 13:51 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  21. 2026-09-27 13:48 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  22. 2026-09-26 15:59 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  23. 2026-09-26 00:27 UTCEPSS rescoreEPSS 1.3% · 69th percentile
  24. 2026-09-23 17:53 UTCEPSS rescoreEPSS 1.2% · 66th percentile
  25. 2026-09-20 20:16 UTCEPSS rescoreEPSS 1.2% · 66th percentile
  26. 2026-09-18 19:28 UTCEPSS rescoreEPSS 1.2% · 66th percentile
  27. 2026-09-16 14:08 UTCEPSS rescoreEPSS 1.2% · 66th percentile
  28. 2026-09-16 05:15 UTCEPSS rescoreEPSS 1.2% · 66th percentile
  29. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  30. 2026-09-12 15:01 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  31. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  32. 2026-09-11 09:37 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  33. 2026-09-11 04:23 UTCOSV refresh
  34. 2026-09-10 09:34 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  35. 2026-09-08 22:00 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  36. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  37. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  38. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  39. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  40. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  41. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.7% · 52nd percentile
  42. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  43. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  44. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  45. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  46. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  47. 2026-08-23 16:47 UTCEG score recompute
  48. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  49. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  50. 2026-08-21 21:44 UTCEG score recompute
  51. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  52. 2026-08-20 18:43 UTCEG score recompute
  53. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  54. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  55. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  56. 2026-08-16 16:50 UTCEG score recompute
  57. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  58. 2026-08-16 03:22 UTCEG score recompute
  59. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  60. 2026-08-15 03:42 UTCEG score recompute
  61. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  62. 2026-08-14 01:55 UTCEG score recompute
  63. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  64. 2026-08-12 22:41 UTCEG score recompute
  65. 2026-08-12 13:51 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  66. 2026-08-11 13:47 UTCEG score recompute
  67. 2026-08-11 00:30 UTCEG score recompute
  68. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  69. 2026-08-09 14:17 UTCEG score recompute
  70. 2026-08-09 13:46 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  71. 2026-08-09 01:26 UTCEG score recompute
  72. 2026-08-08 16:37 UTCEPSS rescoreEPSS 0.7% · 51st percentile
  73. 2026-08-08 02:34 UTCEG score recompute
  74. 2026-08-07 00:53 UTCEG score recompute
  75. 2026-08-06 13:47 UTCEPSS rescoreEPSS 0.7% · 51st percentile

Frequently asked(5)

What is CVE-2026-47101?
CVE-2026-47101 is a high-severity vulnerability; its CVE record was published on May 21, 2026. LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit. When generating a key, the allowed_routes field is stored without verifying that the specified routes fall within the user's own permissions. A key created with…
When was CVE-2026-47101 made public?
CVE-2026-47101 was made public on April 27, 2026: that is the date its CVE record's CNA, VulnCheck, gives for when the vulnerability was made public. The CVE record itself was published on May 21, 2026. EchelonGraph's copy of the record carries a last-modified date of October 8, 2026; the record at its source may have been updated since.
Is CVE-2026-47101 actively exploited?
CVE-2026-47101 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 1.2% probability of exploitation in the next 30 days (67th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-47101?
CVE-2026-47101 has a CVSS base score of 8.8 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-47101?
A fix for CVE-2026-47101 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-47101 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-2026-47101

Explore →

Is Your Infrastructure Affected by CVE-2026-47101?

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