SGLang-0.5.9-RCE

SGLang SSTI to RCE PoC — Unsandboxed Jinja2 Chat Template Rendering CVE-2026-5760 Remote Code Execution via Server-Side Template Injection SSTI in SGLang's reranking endpoint. A malicious GGUF model file with a crafted tokenizer.chattemplate achieves arbitrary code execution when loaded into SGLa...

CVE-2026-52132

A flaw was found in llama.cpp. A remote attacker can exploit this vulnerability when the application is started with the --reranking flag. By sending a POST request to the /rerank endpoint with a negative topn value, the attacker can cause a std::badalloc error and an HTTP 500 response, leading t...

vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the flash late-interaction query cache reaches. Summary On late-interaction /score and /rerank deployments...

GHSA-2PHQ-3PHC-84PX vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the flash late-interaction query cache reaches. Summary On late-interaction /score and /rerank deployments...

PYSEC-2026-4198

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

PYSEC-2026-4198

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755 vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755

The vLLM inference and serving engine (prior to version 0.30.0 ) is vulnerable to a cross-request integrity break in its flash late-interaction scoring at the /score and /rerank endpoints. The root cause is that the system derives the query_key value from the caller-controlled X-Request-Id header...

CVE-2026-105755 vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

PT-2026-106265

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.30.0 Description In deployments using flash late-interaction scoring, the engine derives worker cache keys for query embeddings from the X-Request-Id header, which is controlled by the caller. A concurrent request that...

Linux Distros Unpatched Vulnerability : CVE-2026-52132

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service std::badalloc and HTTP 500 via a...

CVE-2026-52132

llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service std::badalloc and HTTP 500 via a negative topn value in a POST request to /rerank...

CVE-2026-52132

llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service std::badalloc and HTTP 500 via a negative topn value in a POST request to /rerank...

CVE-2026-52132

The llama.cpp software (versions through commit 97f06e9 ) is vulnerable to a Denial of Service (DoS) attack when started with the --reranking flag. A remote attacker can trigger a std::bad_alloc memory allocation failure and an HTTP 500 error by sending a negative value for the top_n variable in ...

CVE-2026-52132

llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service std::badalloc and HTTP 500 via a negative topn value in a POST request to /rerank...

CVE-2026-52132

llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service std::badalloc and HTTP 500 via a negative topn value in a POST request to /rerank...

CVE-2026-52132: Uncontrolled Recursion

llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service std::badalloc and HTTP 500 via a negative topn value in a POST request to /rerank...

CVE-2026-52132

llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service std::badalloc and HTTP 500 via a negative topn value in a POST request to /rerank...