PT-2026-116070

Cube-studio through 2026.09.01 contains an insecure direct object reference vulnerability that allows authenticated users to stop, reset, clear or redeploy other users' notebooks and services by id. Attackers can pass sequential ids to lifecycle endpoints in view notebook.py, view...

Authorization Bypass Through User-Controlled Key

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Authorization Bypass Through User-Controlled Key in flashlateinteractionencodequeries and flashlateinteractionencodedocs in...

PT-2026-105854

Summary The / csp endpoint accepts unauthenticated JSON reports and logs user-controlled values directly to stdout using print without escaping control characters. A remote attacker can include ANSI/VT100 escape sequences in fields such as blocked-uri or document-uri. When the logs are viewed in ...

CVE-2026-73559

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompttoseq in vllm/renderers/inputs/preprocess.py and...

CVE-2026-54236: Insertion of Sensitive Information into Log File

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 sanitizemessage helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo...