MediumVulnerabilityLLM-specific

CVE-2026-73555: vLLM information disclosure via malformed JSON requests

Source: NVD(opens in a new tab)
Identifier: CVE-2026-73555
Published: August 13, 2026
Record updated: October 9, 2026

Affected: vllm < 0.26.0
Fixed in: 0.26.0
released July 25, 2026, 19 days before disclosure
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

vLLM versions prior to 0.26.0 leak internal details in validation error responses. The validation_exception_handler in vllm/entrypoints/openai/server_utils.py converts RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py fails to strip traceback-style file paths. An unauthenticated attacker sending malformed JSON to /v1/chat/completions, /v1/completions, /tokenize, or /detokenize can learn the OS username, home and virtual-environment paths, Python version, internal package structure, line numbers, and endpoint handler names.

Mitigation

Fixed in 0.26.0.

Details

Scores and exploitation

CVSS score: 5.3(medium)
Patch available: Yes
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: none
EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 14, 2026.
Disclosure date: August 13, 2026

Weaknesses and techniques

Weakness (CWE): CWE-209
Attack pattern (CAPEC): CAPEC-54

Affected

Packages: vllm@< 0.26.0 (fixed: 0.26.0)

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: API
Impact: Confidentiality
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-73555

First tracked: August 13, 2026 at 02:08 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

vllmPyPILLM dependency since 2023-08-25 · 15 tracked dependents

Topics

Inference infrastructure

Summary

Mitigation

Affected packages in the Exposure Registry

Topics

Related items