CVE-2026-54236

MEDIUMPre-NVD 5.35.3
EchelonGraph scoreMEDIUM confidence

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

Score 5.3 from GitHub Security Advisory (severity: MODERATE) published 2026-06-17. A secondary CVSS source baseline 5.3; sources differ by 0.0.

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

Also known asEUVD-2026-38403 (ENISA EUVD) · GHSA-hgg8-fqqc-vfmw (GitHub Security Advisories) · PYSEC-2026-3408 (OSV.dev)Source: ENISA EUVD

5.3EG
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: 0.9%CVSS: 5.3Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object repr, leaking the heap memory address verbatim in the error.message field of the response body. This vulnerability is fixed in 0.23.1rc0.

CVSS v3
5.3
EG Score
5.3MEDIUMmedium confidence
EG Risk
55
EG Risk 55/100

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)
Severity53% × 45%
Impact severity (EG Severity): CVSS 5.3 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
0.9%
EPSS %ILE
61st
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 (5.3): severity, escalated by confirmed exploitation. This CVE's 5.3 is its impact severity (EG Severity), not escalated.

EG Severity
5.3 MEDIUMCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
EG Likelihood
0.9% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-07). 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 17, 2026

Last Modified

October 25, 2026

Advisory Details (3)

Auto-updated Jun 23, 2026
Patch available. Sources: github_commit, github, github_pr.
GitHub commit

commit 949236297293 (vllm-project/vllm)

Fix landed in vllm-project/vllm commit 949236297293 — awaiting tagged release

https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82
GitHub pull request

[Security] Apply sanitize_message to Anthropic and STT error paths

Fix merged in vllm-project/vllm PR #45119 on 2026-06-11 — awaiting tagged release

https://github.com/vllm-project/vllm/pull/45119
GitHub advisoryMentions a patch (unverified)

vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router (CWE-532) · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw

Vendor Advisories for CVE-2026-54236(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
pipvllm @ 0.24.0 (fixes <= 0.23.0)—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
vllm0.0.1 ... 0.9.2 (89 versions)
  • every version up to 0.24.0: fixed in 0.24.0
  • every version through 0.23.0: no fix on record
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 8× in last 7d / 31× 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 its CVE.org record (CNA or CISA ADP). 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). "EchelonGraph re-scored" is our own recompute of this CVE's score, not an update from a source, and is not counted in the refreshes above. Most recent first.

Showing the most recent 100 of 211 rows 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 111 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-13 16:53 UTCEPSS rescoreEPSS 0.9% · 61st percentile
  2. 2026-11-12 16:34 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  3. 2026-11-11 16:40 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  4. 2026-11-10 16:44 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  5. 2026-11-09 16:35 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  6. 2026-11-08 16:40 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  7. 2026-11-07 19:28 UTCGHSA enrichmentGHSA-hgg8-fqqc-vfmw · GitHub severity MODERATE · GitHub CVSS 5.3
  8. 2026-11-07 19:28 UTCEchelonGraph re-scored
  9. 2026-11-07 16:39 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  10. 2026-11-06 16:38 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  11. 2026-11-05 16:38 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  12. 2026-11-04 16:35 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  13. 2026-11-03 16:48 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  14. 2026-11-02 16:45 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  15. 2026-11-01 16:34 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  16. 2026-10-31 16:33 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  17. 2026-10-30 16:34 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  18. 2026-10-29 16:33 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  19. 2026-10-28 16:32 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  20. 2026-10-27 16:32 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  21. 2026-10-26 16:31 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  22. 2026-10-25 23:37 UTCEchelonGraph re-scored
  23. 2026-10-25 16:33 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  24. 2026-10-25 14:19 UTCEchelonGraph re-scored
  25. 2026-10-24 16:33 UTCEPSS rescoreEPSS 0.9% · 60th percentile
Show 75 more
  1. 2026-10-23 16:32 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  2. 2026-10-22 21:23 UTCEchelonGraph re-scored
  3. 2026-10-22 16:34 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  4. 2026-10-21 16:33 UTCEPSS rescoreEPSS 0.9% · 60th percentile
  5. 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  6. 2026-10-19 16:32 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  7. 2026-10-18 16:32 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  8. 2026-10-18 03:31 UTCEchelonGraph re-scored
  9. 2026-10-17 16:34 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  10. 2026-10-16 16:42 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  11. 2026-10-15 16:32 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  12. 2026-10-14 16:33 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  13. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  14. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  15. 2026-10-12 15:56 UTCEchelonGraph re-scored
  16. 2026-10-11 19:39 UTCEchelonGraph re-scored
  17. 2026-10-11 16:55 UTCEchelonGraph re-scored
  18. 2026-10-11 14:18 UTCEchelonGraph re-scored
  19. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  20. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  21. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  22. 2026-10-08 17:12 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  23. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  24. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  25. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  26. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  27. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  28. 2026-10-03 06:09 UTCOSV refresh
  29. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  30. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  31. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  32. 2026-09-29 15:22 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  33. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  34. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  35. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  36. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  37. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  38. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  39. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  40. 2026-09-17 19:31 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  41. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  42. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  43. 2026-09-14 03:08 UTCEchelonGraph re-scored
  44. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  45. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  46. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  47. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  48. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  49. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  50. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  51. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  52. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  53. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  54. 2026-08-30 22:26 UTCEchelonGraph re-scored
  55. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  56. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  57. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  58. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  59. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  60. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  61. 2026-08-25 06:16 UTCEchelonGraph re-scored
  62. 2026-08-23 04:29 UTCEchelonGraph re-scored
  63. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  64. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  65. 2026-08-21 07:24 UTCEchelonGraph re-scored
  66. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  67. 2026-08-20 08:16 UTCEchelonGraph re-scored
  68. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  69. 2026-08-19 08:12 UTCEchelonGraph re-scored
  70. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  71. 2026-08-17 15:27 UTCEchelonGraph re-scored
  72. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  73. 2026-08-16 16:20 UTCEchelonGraph re-scored
  74. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  75. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.8% · 54th percentile

Public detection templates

(1 reference)

A public Nuclei detection template is referenced for this CVE. A detection template checks whether a system is affected; it is not necessarily exploit code.

  • Nucleihttp/cves/2026/CVE-2026-54236.yaml
    Published Jun 22, 2026

    vLLM <= 0.23.0 - Anthropic Router Heap Address Information Leak

    Open source ↗

Frequently asked(5)

What is CVE-2026-54236?
CVE-2026-54236 is a medium-severity vulnerability; its CVE record was published on June 17, 2026. vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo…
When was the CVE record for CVE-2026-54236 published?
The CVE record for CVE-2026-54236 was published on June 17, 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-2026-54236 actively exploited?
CVE-2026-54236 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.9% probability of exploitation in the next 30 days (61st percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-54236?
CVE-2026-54236 has a CVSS base score of 5.3 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-54236?
A fix for CVE-2026-54236 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-54236 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-2026-54236

Explore →

Is Your Infrastructure Affected by CVE-2026-54236?

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