https://vulnerability.circl.lu Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Wed, 07 Oct 2026 06:20:27 +0000 https://vulnerability.circl.lu/vuln/fkie_cve-2026-105756 <p>vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0.</p> <p>vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0.</p> https://vulnerability.circl.lu/vuln/fkie_cve-2026-105756 https://vulnerability.circl.lu/vuln/ghsa-2823-qmq8-rwvj <p><strong>Affected:</strong> PyPI: vllm</p> <p>## Affected</p> <p>- **Ecosystem / package:** pip / `vllm` - **Affected versions:** vLLM ≤ 0.25.1 (confirmed on 0.25.1, commit [`752a3a504485`](https://github.com/vllm-project/vllm/tree/752a3a504485790a2e8491cacbb35c137339ad34)). The lower bound predates 0.25.1; maintainers can confirm how far back the loose `cache_salt` validator and unguarded scheduling-path lookup reach.</p> <p>## Summary</p> <p>vLLM&#39;s OpenAI-compatible request models (Completions, Chat Completions, Responses) accept a client-supplied `cache_salt` field and validate it only as &#34;must be a non-empty string&#34; — no character or length restrictions. On a deployment with the built-in LMCache-MP KV connector enabled, that value is stored verbatim on the request tracker and forwarded unguarded as a keyword argument into the scheduler&#39;s per-step cache lookup. The downstream LMCache library applies a *stricter* check in `IPCCacheServerKey.__post_init__`, which raises `ValueError` for any `cache_salt` containing `@`, `/`, `\`, or NUL (or longer than 128 characters).</p> <p>Neither the LMCache-MP connector lookup call site nor `Scheduler.schedule()` wraps that call in a request-scoped `try`/`except`, so the `ValueError` propagates uncaught into `EngineCore`&#39;s top-level handler, which treats any uncaught exception as fatal and kills the whole engine process. A single publicly reachable request with, for example, `cache_salt=&#34;/&#34;` therefore takes down the engine for all concurrent users. vLLM&#39;s boundary validator is looser than the downstream c…</p> <p><strong>Affected:</strong> PyPI: vllm</p> <p>## Affected</p> <p>- **Ecosystem / package:** pip / `vllm` - **Affected versions:** vLLM ≤ 0.25.1 (confirmed on 0.25.1, commit [`752a3a504485`](https://github.com/vllm-project/vllm/tree/752a3a504485790a2e8491cacbb35c137339ad34)). The lower bound predates 0.25.1; maintainers can confirm how far back the loose `cache_salt` validator and unguarded scheduling-path lookup reach.</p> <p>## Summary</p> <p>vLLM&#39;s OpenAI-compatible request models (Completions, Chat Completions, Responses) accept a client-supplied `cache_salt` field and validate it only as &#34;must be a non-empty string&#34; — no character or length restrictions. On a deployment with the built-in LMCache-MP KV connector enabled, that value is stored verbatim on the request tracker and forwarded unguarded as a keyword argument into the scheduler&#39;s per-step cache lookup. The downstream LMCache library applies a *stricter* check in `IPCCacheServerKey.__post_init__`, which raises `ValueError` for any `cache_salt` containing `@`, `/`, `\`, or NUL (or longer than 128 characters).</p> <p>Neither the LMCache-MP connector lookup call site nor `Scheduler.schedule()` wraps that call in a request-scoped `try`/`except`, so the `ValueError` propagates uncaught into `EngineCore`&#39;s top-level handler, which treats any uncaught exception as fatal and kills the whole engine process. A single publicly reachable request with, for example, `cache_salt=&#34;/&#34;` therefore takes down the engine for all concurrent users. vLLM&#39;s boundary validator is looser than the downstream c…</p> https://vulnerability.circl.lu/vuln/ghsa-2823-qmq8-rwvj