Know every vulnerabilitybefore it knows you.
DevGuard continuously monitors your dependencies and alerts you when CVEs like this one affect your stack — with real-time threat intelligence built for developers.
CVE-2026-105752
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cache_salt value, placing the continuation prefix in the global unsalted cache namespace even when the caller enabled salting. On deployments with prefix caching enabled, which is the default, an authenticated tenant who can reconstruct a victim's low-entropy post-tool history can submit the same continuation and use the cached_tokens_per_turn count to determine whether the prefix was previously processed, defeating the intended tenant isolation of salted prefix caching. This issue is fixed in version 0.30.0.
Upload your own SBOM in CycloneDX 1.6 or higher (JSON) directly here to check your vulnerabilities.
Drag and drop some file here, or click to select
The vulnerability can be exploited over the network without needing physical access. It is difficult for an attacker to exploit this vulnerability and may require special conditions. An attacker needs basic access or low-level privileges. No user interaction is needed for the attacker to exploit this vulnerability. The impact is confined to the system where the vulnerability exists. There is a low impact on the integrity of the data.
Limited exploitation activity has been observed. Close monitoring and planned remediation are recommended.
The exploit probability is very low. The vulnerability is unlikely to be exploited in the next 30 days.
We did not find any exploit available. Neither in GitHub repositories nor in the Exploit-Database.
Browse More
Continuously monitor your dependencies and get alerted when vulnerabilities like this one affect your stack.
Checkout DevGuard