77 matches found
CVE-2026-114049 vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense
vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense that allows remote attackers to constrain other clients' outputs by leaving stale allowedtokenids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycl...
CVE-2026-114049 vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense
vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense that allows remote attackers to constrain other clients' outputs by leaving stale allowedtokenids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycl...
CVE-2026-114049
Versions of vLLM prior to 0.31.0 are vulnerable to a cross-request mask leak within the InputBatch.condense() function. This flaw occurs because the application leaves stale allowed_token_ids rows, which can then be applied to subsequent requests. A remote attacker can exploit this by submitting ...
Use of Cache Containing Sensitive Information
Overview next is a react framework. Affected versions of this package are vulnerable to Use of Cache Containing Sensitive Information via cross-request deduplication in the 'use cache' mechanism, where draft mode state is not accounted for when sharing cached fills between concurrent requests. A...
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...
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...
Use of Cache Containing Sensitive Information
Overview next is a react framework. Affected versions of this package are vulnerable to Use of Cache Containing Sensitive Information via cross-request deduplication in the use-cache-wrapper.ts cache function, where draft mode state is not accounted for when sharing cached fills across concurrent...
CVE-2026-100379 Cross-request disclosure of CentralAuth cookies in Wikipedia Android App
Exposure of Sensitive Information to an Unauthorized Actor vulnerability in Wikimedia Foundation Wikipedia Android App allows Accessing/Intercepting/Modifying HTTP Cookies. This issue affects Wikipedia Android App: main...
CVE-2026-100379 Cross-request disclosure of CentralAuth cookies in Wikipedia Android App
Exposure of Sensitive Information to an Unauthorized Actor vulnerability in Wikimedia Foundation Wikipedia Android App allows Accessing/Intercepting/Modifying HTTP Cookies. This issue affects Wikipedia Android App: main...
CVE-2026-93989 vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words
vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...
CVE-2026-92708 devalue: Cross-request process memory disclosure in devalue when `stringify` / `uneval` serialize Node Buffers
Svelte devalue is a JavaScript library that serializes values into strings when JSON.stringify isn't sufficient for the job. In versions 5.1.0 through 5.9.2, stringify and uneval functions serialize a typed array by emitting its entire backing ArrayBuffer rather than only the view, so serializing...
CVE-2026-92708
Svelte devalue is a JavaScript serialization library for use with SvelteKit, Nuxt, and other frameworks. In versions 5.1.0 through 5.9.2 , the stringify and uneval functions serialize a typed array by emitting its entire backing ArrayBuffer rather than only the view. Since a Node Buffer's backing...
CVE-2026-93840
vLLM before 0.29.0 is vulnerable to cross-request logits corruption via the allowed_token_ids parameter. The root cause is in SamplingParams._validate_allowed_token_ids() , which validates token IDs against the tokenizer length rather than the model output logits width. An attacker can supply tok...
CVE-2026-93840 vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids
vLLM before 0.29.0 validates allowedtokenids against tokenizer length instead of model output logits width in SamplingParams.validateallowedtokenids. Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow...
Astra Linux – Vulnerability in Jetty9
In Eclipse Jetty versions 9.4.0 to 9.4.56, a buffer can be released incorrectly when encountering a gzip error during the inflation of a request body. This can lead to corrupted data and/or inadvertent sharing of data between requests...
CVE-2026-84685 Improper Cache Isolation in auth0/react-native-auth0 SDK Web Platform Credential Management
The react-native-auth0 SDK's web platform implementation does not scope its in-memory token cache to individual user sessions when operating in a server-side rendering SSR environment where module state persists across HTTP requests. Under the listed preconditions, tokens cached in module memory...
CVE-2026-61397 Apache CloudStack: OAuth2 Token Cross-Request Leak
Exposure of Sensitive Information to an Unauthorized Actor vulnerability in Apache CloudStack's OAuth2 authentication plugin and Google OAuth integration. This issue affects Apache CloudStack: from 4.19.0.0 through 4.20.3.0 and from 4.21.0.0 through 4.22.1.0. Users are recommended to upgrade to...