vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages
CVE-2026-73555 · GHSA-hwrm-c4cx-rf4j · published 2026-09-04
- Severity
- Medium
- CVSS score
- 5.3
- Chance of exploitation (EPSS)
- 0.41%
- Fixed in
- 0.26.0
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Partial
- CISA SSVC
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., ) 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.
Upgrade vllm to 0.26.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
Two possible fixes (either suffices): Option A — Fix validationexceptionhandler: 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 sanitizemessage:** Add a regex to strip File "...", line \d+ patterns, similar to how memory addresses are already stripped: Option A is preferred as it addresses the root cause rather than filtering symptoms.
Deploying vLLM behind a reverse proxy that rewrites error response bodies to strip file paths would mitigate this, though it is fragile.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | < 0.26.0 | 0.26.0 |
- CriticalPhoenix: Format String Injection in applyChatTemplatearize-phoenix
- CriticalFlowise: Unauthenticated OAuth2 token refresh endpoint returns access tokens — enables token theft for any connected serviceflowise
- CriticalMLflow: Environment variable injection in AI Gateway secrets enables server-side credential exfiltrationmlflow
- HighConfig revision hashes could expose password verifiersopenclaw
- Highn8n: Shared Credential Header Leak via HTTP Request Pagination Expressionn8n, n8n, n8n
- HighWorkspace dotenv files could override provider credentialsopenclaw
- CriticalvLLM: OpenAI auth bypassvllm
- CriticalvLLM has RCE In Video Processingvllm
- CriticalvLLM Allows Remote Code Execution via PyNcclPipe Communication Servicevllm
- CriticalvLLM Vulnerable to Remote Code Execution via Mooncake Integrationvllm
- CriticalCVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0vllm
- CriticalvLLM Deserialization of Untrusted Data vulnerabilityvllm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.