vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
CVE-2026-54236 · GHSA-hgg8-fqqc-vfmw · published 2026-06-17 · updated 2026-07-20
- Severity
- Medium
- CVSS score
- 5.3
- Chance of exploitation (EPSS)
- 0.93%
- Fixed in
- 0.24.0
- Exploitation Public proof of concept
- Automatable Yes
- Technical impact Partial
- CISA SSVC
The fix for CVE-2026-22778 / GHSA-4r2x-xpjr-7cvv (PRs #31987 and #32319) introduced sanitizemessage and applied it at four FastAPI exception-handling sites in the OpenAI router. The sanitizer strips object-repr memory addresses ( → ) before error messages reach the client, defeating the ASLR-bypass primitive that CVE-2026-22778 chained with a libopenjp2 heap overflow for RCE. The fix is incomplete: response paths added to vLLM at or after the same time as the fix continue to echo str(exc) directly to clients without sanitizemessage.
Upgrade vllm to 0.24.0 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.
Researcher: Kai Aizen — SnailSploit (@SnailSploit), Adversarial & Offensive Security Research Severity: CVSS 3.1 5.3 (Medium) AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N Target: https://github.com/vllm-project/vllm ---
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | <= 0.23.0 | 0.24.0 |
- 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.