Poznaj podatności. Chroń swoje aplikacje.
Dowiedz się, które luki zagrażają Twoim technologiom i jak je usunąć. Znajdziesz tu opisy zagrożeń, podatne wersje i konkretne zalecenia - od CMS-ów i wtyczek po biblioteki aplikacji.
Archiwum podatności 100
Wyczyść filtryvLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers
vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds
vLLM: Cross-User Data Leak Vulnerability
vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages
vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of GHSA-rwxx-mrjm-wc2m
vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to ini
vLLM: Completion prompt lists fan out into unbounded engine requests
atomic-agents-stack: Parallel helper/delegate batch reserves $0 for models absent from the pricing table, bypassing the cost-cap fan-out guard
vLLM has Remote DoS via Invalid Recovered Token Reinjection
LMCache: 16-bit multimodal hash collision can poison KV cache entries
vLLM: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations
vLLM: OOM Denial of Service via Audio Decompression Bomb
vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
vllm has Improper Resource Shutdown or Release
lmdeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out
vLLM Vulnerable to Remote DoS via Special-Token Placeholders
vLLM: Server-Side Request Forgery (SSRF) in `download_bytes_from_url `
vLLM has SSRF Protection Bypass
vLLM vulnerable to Server-Side Request Forgery (SSRF) through MediaConnector
Dowiedz się, które podatności dotyczą Twojej aplikacji
Po podłączeniu integracji DockRay i włączeniu raportowania oprogramowania DockRay porównuje zgłoszone wersje komponentów ze znanymi podatnościami i powiadamia o potwierdzonych dopasowaniach. Zakres zależy od obsługiwanej technologii i dostępnych biuletynów.