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 152
Reset filtersvLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`
LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation
Picklescan is vulnerable to RCE through missing detection when calling numpy.f2py.crackfortran.myeval
Picklescan missing detection when calling pytorch function torch.jit.unsupported_tensor_ops.execWrapper
Picklescan missing detection when calling built-in python library function timeit.timeit()
Picklescan has a missing detection when calling built-in python idlelib.autocomplete.AutoComplete.fetch_completions
Picklescan has a missing detection when calling built-in python profile.Profile.runctx
MONAI: Unsafe deserialization in NumpyReader allows arbitrary code execution via malicious .npy files
In MONAI 1.6.0, PersistentDataset (monai/data/dataset.py) explicitly rejects the combination track_meta=True with weights_only=True, forcing users who cache MetaTensors (the default tensor type in MON
vLLM: Cross-User Data Leak Vulnerability
vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
NLTK: Allowlisted pickle loaders still permit code execution in current source
Keras: TorchModuleWrapper can deserialize unsafe PyTorch pickle data
vLLM has Remote DoS via Invalid Recovered Token Reinjection
PyTorch Lightning allows arbitrary code execution through checkpoint _instantiator hyperparameters
mcp-memory-service: Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete
Stanza: Remote Code Execution via Unsafe Pickle Deserialization in Model Loaders
vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
lmdeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out
Cleartext storage of HMAC signing key in Amazon SageMaker Python SDK ModelBuilder/Serve path
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.