Understand vulnerabilities. Protect your applications.
Discover which vulnerabilities affect your technologies and how to fix them. Explore clear explanations, affected versions and practical recommendations - from CMS platforms and plugins to application libraries.
Vulnerability archive 100
Reset filtersvLLM 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
Know which vulnerabilities affect your application
With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.