CVE-2026-73555

MEDIUMPre-NVD 5.35.3—
EchelonGraph scoreMEDIUM confidence

This medium-severity CVE scores 5.3 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.3%, top 83% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, secondary
5.3EG
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 5.3Exploit: None knownExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/entrypoints/openai/server_utils.py converts FastAPI RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py does not remove traceback-style file paths, allowing unauthenticated malformed JSON requests to /v1/chat/completions, /v1/completions, /tokenize, and /detokenize to disclose the OS username, home and virtual-environment paths, Python version, internal package structure, line numbers, and endpoint handler names. This issue is fixed in version 0.26.0.

CVSS v3
5.3
EG Score
5.3(medium)
EG Risk
39(Track)
EG Risk 39/100SSVC: Track

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
Severity53% × 45%
Exploitation0% × 40%
Automatability100% × 15%
Action: Routine — remediate on your standard cadence.
EPSS PROB
0%
EPSS %ILE
17%
KEV
Not listed

Published

August 13, 2026

Last Modified

August 14, 2026

Advisory Details (4)

Auto-updated Aug 13, 2026
Patch available. Sources: github_commit, github_pr, github_release, github.
github Patch Available

Unauthenticated Internal Path and Username Disclosure via Validation Error Messages · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-hwrm-c4cx-rf4j
github_release Patch Available

v0.26.0

Patch available: vllm-project/vllm v0.26.0

https://github.com/vllm-project/vllm/releases/tag/v0.26.0
github_pr

Sanitize server file paths from validation error responses

Fix merged in vllm-project/vllm PR #46415 on 2026-07-09 — awaiting tagged release

https://github.com/vllm-project/vllm/pull/46415
github_commit

commit e87521626feb (vllm-project/vllm)

Fix landed in vllm-project/vllm commit e87521626feb — awaiting tagged release

https://github.com/vllm-project/vllm/commit/e87521626febe2763f997691d1599de4175f4324

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 10× in last 7d / 28× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. 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. Most recent first.

  1. 2026-08-26 14:47 UTCEPSS rescore
  2. 2026-08-25 20:40 UTCEG score recompute
  3. 2026-08-25 13:49 UTCEPSS rescore
  4. 2026-08-24 20:07 UTCEG score recompute
  5. 2026-08-23 19:46 UTCEG score recompute
  6. 2026-08-23 00:19 UTCEPSS rescore
  7. 2026-08-22 19:27 UTCEG score recompute
  8. 2026-08-21 23:49 UTCEPSS rescore
  9. 2026-08-21 19:07 UTCEG score recompute
  10. 2026-08-20 22:56 UTCEPSS rescore
  11. 2026-08-19 18:27 UTCEG score recompute
  12. 2026-08-19 17:04 UTCEPSS rescore
  13. 2026-08-18 18:06 UTCEG score recompute
  14. 2026-08-18 13:49 UTCEPSS rescore
  15. 2026-08-18 13:49 UTCEPSS rescore
  16. 2026-08-17 17:32 UTCEG score recompute
  17. 2026-08-17 13:47 UTCEPSS rescore
  18. 2026-08-16 17:12 UTCEG score recompute
  19. 2026-08-16 14:56 UTCEPSS rescore
  20. 2026-08-16 14:56 UTCEPSS rescore
  21. 2026-08-16 02:15 UTCEPSS rescore
  22. 2026-08-15 16:52 UTCEG score recompute
  23. 2026-08-15 01:31 UTCEPSS rescore
  24. 2026-08-14 16:32 UTCEG score recompute
  25. 2026-08-14 16:04 UTCEG score recompute
Show 3 more
  1. 2026-08-13 15:23 UTCEG score recompute
  2. 2026-08-13 15:12 UTCEG score recompute
  3. 2026-08-13 15:11 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-73555?
CVE-2026-73555 is a medium vulnerability published on August 13, 2026. vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validationexceptionhandler in vllm/entrypoints/openai/serverutils.py converts FastAPI RequestValidationError objects with str(exc), and sanitizemessage in vllm/entrypoints/utils.py does not remove…
When was CVE-2026-73555 disclosed?
CVE-2026-73555 was first published in the National Vulnerability Database on August 13, 2026, with the most recent update on August 14, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-73555 actively exploited?
CVE-2026-73555 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0% probability of exploitation in the next 30 days, which ranks it in the top 83.2% of all scored CVEs.
What is the CVSS score of CVE-2026-73555?
CVE-2026-73555 has a CVSS v3 base score of 5.3 (NVD).
How do I remediate CVE-2026-73555?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-73555, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-73555

Explore →

Is Your Infrastructure Affected by CVE-2026-73555?

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

Start Free Scan →Browse All CVEs