Showing 25 vulnerabilities on this page for Red Hat AI Inference Server

Signals CISA KEV Ransomware Nuclei
Red Hat vulnerability results
VulnerabilityTitle and contextCVSSEPSSPoCsSignalsSTIX action

Data-sciences-pipeline: dsp: v1 argo template path accepts arbitrary workflow spec, bypassing all v2 security hardening

A flaw was found in Data Science Pipelines (DSP). An attacker with namespace editor privileges can bypass security hardening by submitting a malicious Argo Workflow through the V1 API path. This allows the API server to create pods with elevated privileges, acting as a 'confused deputy' on behalf of the attacker. Successful exploitation grants the attacker node-root access, enabling arbitrary code execution and full control over the underlying node.

CWE-266Aug 10, 2026
CVSS7.6v3.1EPSS0.35%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

FFmpeg - Out-of-Bounds Write in RASC Decoder decode_dlta()

FFmpeg's RASC video decoder (decode_dlta in libavcodec/rasc.c) performs 32-bit reads and writes at the row cursor before the NEXT_LINE row-boundary check and validates the DLTA region in pixel rather than byte units, so a DLTA run on a PAL8 frame can access several bytes past the row allocation. A crafted media stream using the RASC FourCC, decoded by libavcodec, triggers a bitstream-controlled out-of-bounds heap write and adjacent out-of-bounds read, leading to memory corruption.

CWE-787Jun 28, 2026
CVSS8.8v4.0EPSS0.275%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

jackson-databind: Array subtype allowlist bypass in BasicPolymorphicTypeValidator (allowIfSubTypeIsArray)

jackson-databind contains the general-purpose data-binding functionality and tree-model for Jackson Data Processor. From 2.10.0 until 2.18.8, 2.21.4, and 3.1.4, BasicPolymorphicTypeValidator.Builder.allowIfSubTypeIsArray() allowlists any array type based only on clazz.isArray(), without validating the array's component (element) type against the configured allowlist. A PTV built with allowIfSubTypeIsArray() plus an explicit concrete-type allowlist therefore still permits EvilType[] even though E

CWE-184Jun 23, 2026
CVSS8.1v3.1EPSS0.712%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.

CWE-617CWE-94Jun 22, 2026
CVSS7.5v3.1EPSS0.746%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

vLLM: OpenAI auth bypass

vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware. It allows to use the API without providing the configured VLLM_API_KEY or --api-key. This vulnerability is fixed in 0.22.0.

CWE-444CWE-501Jun 22, 2026
CVSS9.1v3.1EPSS1.15%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

vLLM - Denial of Service via Unvalidated Multimodal Embeddings

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose

CWE-20CWE-787Jun 20, 2026
CVSS8.7v4.0EPSS0.352%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Libaom: libaom: remote code execution via svc layer context handling with attacker-controlled frames

A remote code execution vulnerability was found in libaom, the reference AV1 codec implementation. Insufficient bounds validation in the AV1 encoder's SVC (Scalable Video Coding) layer ID control allows an attacker to supply crafted video frame pixels that overlap with internal encoder layer context structures. In fork-based video processing services, an attacker can use this to hijack the cyclic refresh map pointer, brute-force the process base address via a crash oracle, and redirect control f

CWE-787Jun 19, 2026
CVSS7.1v3.1EPSS0.452%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Libaom: libaom: heap-buffer-overflow read via missing bounds check in ctrl_set_layer_id

A heap-buffer-overflow read vulnerability was found in libaom, the reference AV1 codec implementation. A missing bounds check in the SVC (Scalable Video Coding) layer ID control function allows setting a spatial_layer_id exceeding the configured number of layers. This causes an out-of-bounds heap read of approximately 40,728 bytes when computing a layer context array index. An attacker who can influence SVC encoder parameters in a network-facing service could exploit this for information disclos

CWE-125Jun 19, 2026
CVSS7.1v3.1EPSS0.289%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Libaom: libaom: heap buffer overflow in av1 encoder first-pass stats buffer via lap mode

A heap buffer overflow vulnerability was found in libaom, the reference AV1 codec implementation. A flaw in the AV1 encoder's Look-Ahead Processing (LAP) mode causes the first-pass stats ring buffer wrap-around guard to be bypassed when g_lag_in_frames is set to 1 or higher. This results in a 232-byte out-of-bounds write on every encoded frame after the second, corrupting adjacent heap objects. An attacker who can influence encoder configuration in a transcoding service or WebRTC session could e

CWE-122Jun 19, 2026
CVSS7.6v3.1EPSS0.346%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Libaom: libaom: arbitrary address write via svc layer context oob and cyclic refresh map pointer hijack

An arbitrary address write vulnerability was found in libaom, the reference AV1 codec implementation. A missing bounds check in the SVC (Scalable Video Coding) layer ID control function allows an attacker to inject an arbitrary pointer into the cyclic refresh map field via crafted image pixel values. The encoder then writes approximately 1,200 bytes at the attacker-controlled address. This is fully deterministic and does not require a separate information leak. An attacker who can supply frames

CWE-787Jun 19, 2026
CVSS7.1v3.1EPSS0.328%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Heap out-of-bounds write via odd slice_height in FFmpeg MagicYUV decoder

An out-of-bounds write vulnerability in FFmpeg's libavcodec library, specifically in the MagicYUV decoder, allows denial-of-service and, in some cases, can be exploited for remote code execution. This vulnerability is associated with the file libavcodec/magicyuv.C. This issue affects FFmpeg before version 8.1.2.

CWE-787Jun 18, 2026
CVSS8.8v3.1EPSS1.57%PoCs5SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Starlette: SSRF and NTLM credential theft via UNC paths in StaticFiles on Windows

Starlette is a lightweight ASGI framework/toolkit. In versions 1.0.1 and earlier, StaticFiles on Windows is vulnerable to SSRF. An UNC path such as \\attacker.com\share can cause os.path.realpath to initiate an outbound SMB connection before the path is rejected, exposing the service account’s NTLMv2 credentials for offline cracking or relay even though the HTTP response is only a 404. The issue affects default follow_symlink=False deployments, including frameworks built on Starlette such as Fas

CWE-918Jun 17, 2026
CVSS7.5v3.1EPSS0.368%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations

A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB, transparency information may be implicitly discarded or remapped, leading to unexpected rendering of transparent pixels and distortion of input content. This can result in the model misinterpreting image content, potentially

CWE-115CWE-436Jun 17, 2026
CVSS4.8v3.1EPSS0.239%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causin

CWE-400CWE-770Jun 11, 2026
CVSS7.5v3.1EPSS0.543%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Policy Bypass in LightGlue Nested Config Resolution in huggingface/transformers

A vulnerability in the LightGlue model loading path of huggingface/transformers version 5.2.0 allows an attacker-controlled model repository to execute arbitrary code during model initialization. The issue arises because the `trust_remote_code` parameter, intended to prevent remote code execution, is overridden by untrusted serialized configuration data in a nested code path. Specifically, when loading a LightGlue model using `AutoModel.from_pretrained()` with `trust_remote_code=False`, the `Lig

CWE-829Jun 3, 2026
CVSS9.6v3.1EPSS0.547%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

AIOHTTP Vulnerable to Deserialization of Untrusted Data

AIOHTTP is an asynchronous HTTP client/server framework for asyncio and Python. Prior to version 3.14.0, using ``CookieJar.load()`` with untrusted input may allow arbitrary code execution. Most applications using this function will be doing so with the user's own data, so this is unlikely to affect many applications. Version 3.14.0 patches the issue. If an application does allow attacker controlled files to be loaded, a workaround on older releases would be to sanitize the files before loading.

CWE-502Jun 2, 2026
CVSS6.4v3.1EPSS0.179%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

AI Tensor Engine for ROCm (AITER) 0.1.14 Unauthenticated RCE via MessageQueue.recv() Pickle Deserialization

AI Tensor Engine for ROCm (AITER) through 0.1.14 contains an unauthenticated remote code execution vulnerability in the MessageQueue.recv() function within shm_broadcast.py that allows unauthenticated remote attackers to execute arbitrary code by sending a malicious pickle payload to a ZMQ SUB socket with no authentication, HMAC, or format validation. Attackers who can reach the writer XPUB endpoint on the cluster network or supply a forged Handle with an attacker-controlled remote_subscribe_add

CWE-502Jun 1, 2026
CVSS9.2v4.0EPSS1.1%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

pip can extract console_scripts and gui_scripts outside installation directory

pip would treat console_scripts and gui_scripts as paths instead of file names without sanitizing the resolved absolute path to the installation directory, leading to entry points being installed outside the installation directory.

CWE-22Jun 1, 2026
CVSS4.1v4.0EPSS0.32%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

opentelemetry-java: Unbounded Memory Allocation in W3C Baggage Propagation

opentelemetry-java is the Java implementation of the OpenTelemetry API for recording telemetry, and SDK for managing telemetry recorded by the API. Prior to 1.62.0, a vulnerability affects the baggage propagation implementation in opentelemetry-api and opentelemetry-extension-trace-propagators. Parsing oversized baggage causes unbounded memory allocation and CPU consumption. Because baggage is automatically re-injected into every outgoing request, the effect can fan out to downstream services th

CWE-770May 28, 2026
CVSS5.3v3.1EPSS1.1%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

PyJWT: Public-key JWK accepted as HMAC secret enables forged HS256 tokens when mixed families are allowed

PyJWT is a JSON Web Token implementation in Python. Prior to 2.13.0, when the verifier is decoding JSON Web Tokens, while supporting both asymmetric and HMAC algorithms, the library does not validate use of JSON Web Keys in HMAC algorithm, allowing attacker to use the issuer public key as the secret key for HMAC algorithm. This vulnerability is fixed in 2.13.0.

CWE-287CWE-347May 28, 2026
CVSS7.4v3.1EPSS0.395%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Starlette has missing Host header validation that poisons request.url.path, bypassing path-based security checks

Starlette is a lightweight ASGI framework/toolkit. Prior to version 1.0.1, the HTTP `Host` request header was not validated before being used to reconstruct `request.url`. Because the routing algorithm relies on the raw HTTP path while `request.url` is rebuilt from the `Host` header, a malformed header could make `request.url.path` differ from the path that was actually requested. Middleware and endpoints that apply security restrictions based on `request.url` (rather than the raw `scope` path)

CWE-1289CWE-444May 26, 20261 related artifact
CVSS6.5v3.1EPSS1.84%PoCs6SignalsNot listed in CISA KEVNo known ransomware use1 Nuclei templateSTIX

Diffusers: `trust_remote_code` bypass via `custom_pipeline` and local custom components

Diffusers is the a library for pretrained diffusion models. Prior to 0.38.0, a trust_remote_code bypass in DiffusionPipeline.from_pretrained allows arbitrary remote code execution despite the user passing trust_remote_code=False (or omitting it, which is the default). The vulnerability has three variants, all sharing the same root cause — the trust_remote_code gate was implemented inside DiffusionPipeline.download() rather than at the actual dynamic-module load site, so any code path that bypas

CWE-358CWE-94May 14, 2026
CVSS8.8v3.1EPSS0.848%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Compromise of PyTorch Lightning PyPi Package Versions

PyTorch Lightning is a deep learning framework to pretrain and finetune AI models. Versions 2.6.2 and 2.6.2 have introduced functionality consistent with a credential harvesting mechanism.

CWE-506CWE-829May 14, 2026
CVSS9.3v4.0EPSS0.392%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

Python-Multipart: Denial of Service via unbounded multipart part headers

Python-Multipart is a streaming multipart parser for Python. Prior to 0.0.27, python-multipart has a denial of service vulnerability in multipart part header parsing. When parsing multipart/form-data, MultipartParser previously had no limit on the number of part headers or the size of an individual part header. An attacker could send a request with either many repeated headers without terminating the header block or a single very large header value, causing excessive CPU work before request reje

CWE-606CWE-770May 13, 2026
CVSS7.5v3.1EPSS0.74%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX

urllib3: Decompression-bomb safeguards bypassed in parts of the streaming API

urllib3 is an HTTP client library for Python. From 2.6.0 to before 2.7.0, urllib3 could decompress the whole response instead of the requested portion (1) during the second HTTPResponse.read(amt=N) call when the response was decompressed using the official Brotli library or (2) when HTTPResponse.drain_conn() was called after the response had been read and decompressed partially (compression algorithm did not matter here). These issues could cause urllib3 to fully decode a small amount of highly

CWE-409May 13, 2026
CVSS8.9v4.0EPSS0.68%PoCs0SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templatesSTIX