CVE-2026-54236
vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
- 게시됨
- 2026. 6. 22.
- 업데이트됨
- 2026. 6. 23.
- CNA 할당 중
- GitHub_M
기본 CVSS
nvd · CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N낮음 · 다음 30일
- 백분위수
- 60.6%
- 모델 날짜
- 2026. 11. 4.
EPSS는 통계적 추정치이지 확실성이나 영향의 척도가 아닙니다. 이를 CVSS, KEV 상태, 노출 및 환경과 결합하세요.
요약
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object repr, leaking the heap memory address verbatim in the error.message field of the response body. This vulnerability is fixed in 0.23.1rc0.
소스
http/cves/2026/CVE-2026-54236.yaml
Nuclei Templates명시된 조건
- network: http($.protocol_keys)
- verification: dsl($.matchers[*].type)
책임 있는 사용
귀하가 소유하고 있거나 테스트할 권한이 있는 시스템에 대해서만 취약점 정보를 사용하십시오. Kitploit은 공개 연구 메타데이터에 연결되며 익스플로잇 코드나 악성 페이로드를 저장하지 않습니다.