Medium

vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages

  • Disclosed: 04.09.2026
  • Updated: 11.10.2026 15:18

Summary

When the vLLM API receives a malformed request (e.g., invalid JSON or missing required fields), FastAPI raises a Pydantic RequestValidationError. The validation_exception_handler in vllm/entrypoints/openai/server_utils.py converts this exception to a string via str(exc), which includes the internal file path and line number of the handler function. The existing sanitize_message() function in vllm/entrypoints/utils.py strips memory addresses (e.g., 0x7f...) but does not strip File "...", line X patterns. The result is a user-facing HTTP response that leaks internal system information.

Impact

An unauthenticated attacker can extract the following with a single malformed request:

  • OS username running the vLLM process (e.g., ubuntu)
  • Home directory path (e.g., /home/ubuntu/)
  • Virtual environment path (e.g., vllm-env/)
  • Python version (e.g., 3.12)
  • Internal package structure and line numbers (e.g., vllm/entrypoints/openai/chat_completion/api_router.py)
  • Handler function names per endpoint, enabling precise version fingerprinting

This information aids attackers in constructing targeted exploits: environment paths narrow the attack surface, and handler function names + line numbers enable exact version identification even when the /version endpoint is disabled.

All POST endpoints that accept JSON bodies are affected, including /v1/chat/completions, /v1/completions, /tokenize, and /detokenize.

Workarounds

Deploying vLLM behind a reverse proxy that rewrites error response bodies to strip file paths would mitigate this, though it is fragile.

Remediation Recommendation

Two possible fixes (either suffices):

Option A — Fix validation_exception_handler: Construct the error message from exc.errors() (the structured Pydantic error list) rather than str(exc). This avoids the traceback-style string entirely.

Option B — Fix sanitize_message: Add a regex to strip File "...", line \d+ patterns, similar to how memory addresses are already stripped:

python
import re
msg = re.sub(r'File ".*?", line \d+, in \w+', '[internal]', msg)

Option A is preferred as it addresses the root cause rather than filtering symptoms.

Environment Tested

  • vLLM 0.20.1 (pip install, latest stable as of May 2026)
  • Python 3.12
  • Ubuntu 22.04
  • Model: Qwen/Qwen2-0.5B (text-only; bug is model-independent)

This was fixed here: https://github.com/vllm-project/vllm/commit/e87521626f

Affected software

Click a technology to see all vulnerabilities affecting it.

PlatformPackageVulnerable versionsFixed in
Python (PyPI) vllm < 0.26.0 0.26.0

References

CVSS score 5.3/10
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Weakness (CWE)
CWE-209
Platform
Python (PyPI)
Package
vllm
Disclosed
04.09.2026
Updated
11.10.2026 15:18

Sources and licenses

OSV / GitHub Advisory Database - PYSEC-2026-3937 - PyPA Advisory Database; CC BY 4.0

OSV / GitHub Advisory Database - GHSA-hwrm-c4cx-rf4j - CC BY 4.0

Vulnerability history: vllm

All published vulnerabilities of this package (Python (PyPI)), newest first. Shows whether this is a one-off slip or a package that needs watching.

All (94) in the archive
Total entries
94
First → latest
09.2024 10.2026
Without a fix
5
Exploited in attacks
0

Severity breakdown

  • Critical 9
  • High 23
  • Medium 47
  • Low 4
  • Unrated 11

Disclosures per year

  1. 2024: 2
  2. 2025: 30
  3. 2026: 62
Severity:
  1. vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages this entry
    Medium · 5.3 CVE-2026-73555 < 0.26.0 0.26.0
  2. High · 7.5 CVE-2026-54234 >= 0.17.1, < 0.24.0 0.24.0
  3. High CVE-2026-55514 >= 0.12.0, < 0.24.0 0.24.0
  4. Critical · 9.1 CVE-2026-48746 >= 0.3.0, < 0.22.0 0.22.0
  5. Critical · 9.8 CVE-2026-22778 >= 0.8.3, < 0.14.1 0.14.1
  6. High · 8.8 CVE-2026-22807 >= 0.10.1, < 0.14.0 0.14.0
  7. High · 8.8 CVE-2026-56340 >= 0.10.2, < 0.13.0 0.13.0
  8. High · 6.5 CVE-2025-62372 >= 0.5.5, < 0.11.1 0.11.1
  9. High · 8.8 CVE-2025-62164 >= 0.10.2, < 0.11.1 0.11.1
  10. High · 7.5 CVE-2025-59425 < 0.11.0 0.11.0
Show more (13) Showing 20 of 33

Know which vulnerabilities affect your application

With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.

Connect your application
DockRay newsletter

Application security in your inbox

Important vulnerabilities, actionable guidance and practical advice for your applications. Choose your technologies and follow what matters to your project.

  • A daily digest of new vulnerabilities, critical ones included.
  • Notifications about important updates.
  • Practical advice on application security and monitoring.

Leave empty to receive updates for every technology.

Free to subscribe. Unsubscribe with one click in any email.