CVE-2026-42203

HIGHNVD 8.88.8
EchelonGraph scoreMEDIUM confidence

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

This high-severity CVE scores 8.8 under NVD CVSS v3. EPSS exploit probability: 0.7% (50th 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
8.8EG
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: 0.7%CVSS: 8.8Exploit: 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. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.

CVSS v3
8.8
EG Score
8.8HIGHmedium confidence
EG Risk
40
EG Risk 40/100

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)
Severity88% × 45%
The EG Score, 8.8 of 10.
Exploitation0.7% × 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 low or medium mission impact; Track* at high (mission-essential systems).
Exploitation none (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.
EPSS PROB
0.7%
EPSS %ILE
50th
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Track* at high (mission-essential systems).

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

Exploitation none (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.

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 8, 2026

Last Modified

July 15, 2026

Advisory Details (2)

Auto-updated May 8, 2026
Patch available. Sources: github.
GitHub advisoryMentions a patch (unverified)

Server-Side Template Injection in /prompts/test endpoint · Advisory · BerriAI/litellm · GitHub

https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862
Web page

Release v1.83.7-stable · BerriAI/litellm · GitHub

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

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
litellm1.80.10 ... 1.83.6 (43 versions)
  • 1.80.5 up to 1.83.7: fixed in 1.83.7
—

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 11× in last 7d / 27× 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 99 of 175 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. 1 repeat row among the latest 100 is merged into the row it repeats. The 76 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

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

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-42203?
CVE-2026-42203 is a high-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 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the…
When was the CVE record for CVE-2026-42203 published?
The CVE record for CVE-2026-42203 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 July 15, 2026; the record at its source may have been updated since.
Is CVE-2026-42203 actively exploited?
CVE-2026-42203 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.7% probability of exploitation in the next 30 days (50th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-42203?
CVE-2026-42203 has a CVSS v3 base score of 8.8 (NVD).
How do I remediate CVE-2026-42203?
A fix for CVE-2026-42203 is available: update to the fixed version the vendor names in its advisory.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-42203

Explore →

Is Your Infrastructure Affected by CVE-2026-42203?

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

Book a Demo →Browse All CVEs