Vulnerability database
Every flaw the U.S. government’s cybersecurity agency (CISA) has confirmed attackers are using, plus the new WordPress plugin and theme bugs published each day, sorted by what they mean for a small business. We refresh it twice a day. If you see something your website or office runs, tell us.
195 results · page 2 of 4
Aug 13, 2026vLLM is an inference and serving engine for large language models.CVE-2026-73557 · Other software · vllm-project · reported by GitHubMedium 6.3
vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safe_load_prompt_embeds in vllm/renderers/embed_utils.py uses torch.sparse.check_sparse_tensor_invariants, whose process-global save, enable, and restore state can be raced by concurrent prompt_embeds parts submitted to POST /v1/chat/completions through AsyncMultiModalItemTracker.resolve_items, asyncio.gather, and the default executor, allowing an invalid sparse tensor to reach tensor.to_dense despite the CVE-2025-62164 guard when enable_prompt_embeds is enabled. This issue is fixed in version 0.26.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 13, 2026vLLM is an inference and serving engine for large language models.CVE-2026-73556 · Other software · vllm-project · reported by GitHubMedium 5.3
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 13, 2026vLLM is an inference and serving engine for large language models.CVE-2026-73555 · Other software · vllm-project · reported by GitHubMedium 5.3
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/entrypoints/openai/server_utils.py converts FastAPI RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py does not remove traceback-style file paths, allowing unauthenticated malformed JSON requests to /v1/chat/completions, /v1/completions, /tokenize, and /detokenize to disclose the OS username, home and virtual-environment paths, Python version, internal package structure, line numbers, and endpoint handler names. This issue is fixed in version 0.26.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 13, 2026Observable response discrepancy in PostgreSQL SCRAM authentication allows an unauthenticated user to test the existence of a user via observing the SCRAM iteratCVE-2026-14672 · Other software · Postgresql · reported by f86ef6dc-4d3a-42ad-8f28-e6d5547a5007Medium 5.3
Observable response discrepancy in PostgreSQL SCRAM authentication allows an unauthenticated user to test the existence of a user via observing the SCRAM iteration count. This requires the probed user to have a non-default scram_iterations count, because the authentication challenge for a nonexistent user reports the default scram_iterations. Within major versions 16-18, minor versions before PostgreSQL 18.6, 17.11, and 16.15 are affected. Versions before PostgreSQL 16 are unaffected.
- Product
- Postgresql
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 11, 2026The referrer enforcement introduced with TYPO3-CORE-SA-2020-006 (CVE-2020-11069) became ineffective in TYPO3 v13.0, where TYPO3 CMS started serving the backend CVE-2026-19418 · Other software · TYPO3 · reported by f4fb688c-4412-4426-b4b8-421ecf27b14aHigh 7.3
The referrer enforcement introduced with TYPO3-CORE-SA-2020-006 (CVE-2020-11069) became ineffective in TYPO3 v13.0, where TYPO3 CMS started serving the backend and Install Tool applications from the site's main entry script instead of the dedicated typo3/ directory. Whether a request originated from the backend or Install Tool itself was determined by comparing the referrer against the directory of the entry script, which since then is the site root. As a consequence, requests originating from any script running on one of the TYPO3 instance's own domains, such as a frontend page, were accepted by backend routes and Install Tool endpoints. Attackers able to execute JavaScript on one of those domains, for instance by exploiting a cross-site scripting vulnerability, could invoke these endpoints via Fetch/XHR with the privileges of an authenticated victim's user session. This issue affects TYPO3 CMS versions 13.0.0-13.4.33 and 14.0.0-14.3.5.
- Product
- TYPO3 CMS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 10, 2026JetEngine: Does not sanitise uploaded SVG files before storing and serving themCVE-2026-17019 · WordPress plugins & themes · reported by WPScanMedium 6.1
The JetEngine WordPress plugin before 3.8.13.1 does not sanitise uploaded SVG files before storing and serving them, and does not adequately restrict who can upload them, allowing unauthenticated attackers to upload a file containing malicious JavaScript that executes in the browser of any user who opens it (Stored Cross-Site Scripting).
- Product
- JetEngine
- Fixed in
- 3.8.13.1
- What to do
- Update JetEngine to 3.8.13.1 or newer.
Aug 7, 2026Tobit Laboratories AG TeamDavid's Webbox does not enforce authentication or authorization checks when serving these log files.CVE-2026-54201 · Other software · Tobit Laboratories AG · reported by vulnerability@ncsc.chMedium 6.9
Tobit Laboratories AG TeamDavid's Webbox does not enforce authentication or authorization checks when serving these log files. As a result, attackers can obtain sensitive error information or internal application details, potentially aiding in further attacks. This issue affects TeamDavid before Rollout 528. Starting with Rollout 528 (June 30, 2026), the affected functionality is disabled by default and the vulnerabilities are therefore no longer exposed through this functionality.
- Product
- TeamDavid
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordchayns.netlabs.infoguard.ch
Aug 6, 2026OpenChamber 1.11.7 contains a path traversal vulnerability in the file-serving endpoints /api/fs/read, /api/fs/stat, and /api/fs/raw that allows unauthenticatedCVE-2026-53976 · Other software · Bohdan Triapitsyn · reported by VulnCheckCritical 9.3
OpenChamber 1.11.7 contains a path traversal vulnerability in the file-serving endpoints /api/fs/read, /api/fs/stat, and /api/fs/raw that allows unauthenticated remote attackers to read arbitrary files by supplying the allowOutsideWorkspace=true query parameter alongside an absolute path, bypassing the workspace boundary check in resolveReadPathFromContext. Attackers can exploit the vacuous isPathWithinRoot guard to read sensitive files such as the JWT signing secret, SSH private keys, API credentials, and environment variables, enabling full authentication bypass by forging session cookies on password-protected deployments.
- Product
- OpenChamber
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 4, 2026NVIDIA Dynamo for Linux contains a vulnerability in the multimodal serving topology, where an attacker could cause an out-of-bounds write.CVE-2026-24254 · Other software · NVIDIA · reported by psirt@nvidia.comCritical 9.8
NVIDIA Dynamo for Linux contains a vulnerability in the multimodal serving topology, where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, data tampering, denial of service, and information disclosure.
- Product
- Dynamo
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comnvd.nist.gov
Jul 6, 2026vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.CVE-2026-55574 · Other software · vllm-project · reported by GitHubHigh 8.7
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 6, 2026vLLM is a library for LLM inference and serving.CVE-2026-55514 · Other software · vllm-project · reported by GitHubHigh 7.1
vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 6, 2026vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.CVE-2026-54234 · Other software · vllm-project · reported by GitHubHigh 7.5
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 6, 2026vLLM is an inference and serving engine for large language models.CVE-2026-55646 · Other software · vllm-project · reported by GitHubMedium 6.5
vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. This issue is fixed in version 0.24.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 30, 2026A malicious or compromised server can make a DCMTK client using bit-preserving C-GET storage mode write files outside the chosen output directory, using both reCVE-2026-50003 · Other software · OFFIS DICOM · reported by ics-cert@hq.dhs.govCritical 9.3
A malicious or compromised server can make a DCMTK client using bit-preserving C-GET storage mode write files outside the chosen output directory, using both relative (../) paths and absolute paths.
- Product
- DCMTK Toolkit
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 24, 2026In the Linux kernel, the following vulnerability has been resolved: macvlan: fix macvlan_get_size() not reserving space for IFLA_MACVLAN_BC_CUTOFF macvlan_getCVE-2026-53013 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5
In the Linux kernel, the following vulnerability has been resolved: macvlan: fix macvlan_get_size() not reserving space for IFLA_MACVLAN_BC_CUTOFF macvlan_get_size() does not account for IFLA_MACVLAN_BC_CUTOFF, but macvlan_fill_info() conditionally includes it when port->bc_cutoff != 1. This causes nla_put_s32() to fail with -EMSGSIZE when the netlink skb runs out of space, triggering a WARN_ON in rtnetlink and preventing the interface from being dumped. The bug can be reproduced with: ip link add macvlan0 link eth0 type macvlan mode bridge ip link set macvlan0 type macvlan bc_cutoff 0 ip -d link show macvlan0 # fails with -EMSGSIZE The bc_cutoff feature was added in commit 954d1fa1ac93 ("macvlan: Add netlink attribute for broadcast cutoff"), which added the nla_put_s32() call in macvlan_fill_info() but missed adding the corresponding nla_total_size(4) in macvlan_get_size(). A follow-up commit 55cef78c244d ("macvlan: add forgotten nla_policy for IFLA_MACVLAN_BC_CUTOFF") fixed the missing nla_policy entry but still did not fix the size calculation.
- Product
- Linux
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgit.kernel.orggit.kernel.org
Jun 22, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-54236 · Other software · vllm-project · reported by GitHubMedium 5.3
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 sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object r
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-54235 · Other software · vllm-project · reported by GitHubMedium 6.9
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-54233 · Other software · vllm-project · reported by GitHubMedium 6.5
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to ~14.9GB of float32 PCM at decode time. This vulnerability is fixed in 0.23.1rc0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-54232 · Other software · vllm-project · reported by GitHubHigh 8.8
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY="unsafe-best-match" is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-53923 · Other software · vllm-project · reported by GitHubMedium 5.3
vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-48746 · Other software · vllm-project · reported by GitHubCritical 9.1
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.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-47155 · Other software · vllm-project · reported by GitHubMedium 6.5
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 22, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-41523 · Other software · vllm-project · reported by GitHubHigh 7.5
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.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 17, 2026vantage6 is an open-source infrastructure for privacy preserving analysis.CVE-2026-54533 · Other software · vantage6 · reported by GitHubMedium 6.9
vantage6 is an open-source infrastructure for privacy preserving analysis. Prior to version 5.0.0, malicious algorithms can potentially access other algorithms input and output files. Version 5.0.0 fixes the issue. As a workaround, verify and restrict the algorithm containers that are allowed to run on the node.
- Product
- vantage6
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recorddocs.vantage6.aigithub.com
Jun 17, 2026vantage6 is an open-source infrastructure for privacy preserving analysis.CVE-2026-54445 · Other software · vantage6 · reported by GitHubMedium 6.9
vantage6 is an open-source infrastructure for privacy preserving analysis. Versions prior to 5.0.0 provide an initial user with username `root` and password `root`. This is not ideal because attackers know that almost all vantage6 servers have a user with username `root` that probably has admin rights, and the initial password is very weak and it is possible that administrators forget to reset it. Version 5.0.0 fixes the issue. As a workaround, it is possible to delete the `root` user after it has been used to create other users.
- Product
- vantage6
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 17, 2026vantage6 is an open-source infrastructure for privacy preserving analysis.CVE-2024-27928 · Other software · vantage6 · reported by GitHubMedium 5.9
vantage6 is an open-source infrastructure for privacy preserving analysis. Prior to version 5.0.0, if an attacker hacks into a vantage6 user's email account, they can 1) reset the password via email and then 2) reset the 2FA token via email. This way they reduce 2FA to 1FA (email access). Note that most email providers require 2FA to access email, so this issue is not very likely to cause issues. Version 5.0.0 fixes the issue. No known workarounds are available.
- Product
- vantage6
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 17, 2026vantage6 is an open-source infrastructure for privacy preserving analysis.CVE-2024-24769 · Other software · vantage6 · reported by GitHubLow 2.1
vantage6 is an open-source infrastructure for privacy preserving analysis. Prior to version 5.0.0, users can reset their MFA token via API routes that send them an email. Currently the number of emails that is sent is not limited. This gives attackers the option to flood someones mailbox with a lot of emails, and would have adverse effects on the SMTP server which may be seen as spam sender. Note resetting the MFA token requires a correct password, so the potential impact for this is very low. Version 5.0.0 fixes the issue. No known workarounds are available.
- Product
- vantage6
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 11, 2026Summarize before 0.17.0 contains a resource exhaustion vulnerability that allows remote attackers to cause disk exhaustion by serving media responses that bypasCVE-2026-53781 · Other software · steipete · reported by VulnCheckMedium 5.3
Summarize before 0.17.0 contains a resource exhaustion vulnerability that allows remote attackers to cause disk exhaustion by serving media responses that bypass the enforced size limit through missing or misreported Content-Length headers, chunked transfer encoding, or failed HEAD requests. Attackers who control a podcast feed or media URL can stream an unbounded response to local storage via the temp-file download path, exhausting disk or system resources on the host running the CLI.
- Product
- summarize
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 9, 2026LMDeploy is a toolkit for compressing, deploying, and serving large language models.CVE-2026-46517 · Other software · InternLM · reported by GitHubHigh 7.8
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, hardcoded "trust_remote_code=True" enables HF supply-chain RCE without user opt-in. Version 0.13.0 patches the issue.
- Product
- lmdeploy
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 9, 2026LMDeploy is a toolkit for compressing, deploying, and serving large language models.CVE-2026-46432 · Other software · InternLM · reported by GitHubHigh 7.8
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trust_remote_code=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no publicly available patches.
- Product
- lmdeploy
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jun 9, 2026This issue can occur when running an aggregation pipeline that uses the internal $exchange stage configured with key-range partitioning and order-preserving delCVE-2026-9749 · Other software · MongoDB · reported by cna@mongodb.comHigh 7.1
This issue can occur when running an aggregation pipeline that uses the internal $exchange stage configured with key-range partitioning and order-preserving delivery. If a single key range produces enough documents to fill its exchange buffer (that is, many results are routed to the same consumer), the server reaches the code path where a full per-consumer buffer is detected but the internal "high watermark" for that key range is not updated as intended.
- Product
- MongoDB Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
May 27, 2026BentoML is a Python library for building online serving systems optimized for AI apps and model inference.CVE-2026-44346 · Other software · bentoml · reported by GitHubHigh 8.8
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.39, a malicious bentofile.yaml containing a newline-injected value in envs[*].name produces unquoted RUN directives in the BentoML-generated Dockerfile. When the victim runs bentoml containerize on the imported bento, those RUN directives execute on the host during docker build. This vulnerability is fixed in 1.4.39.
- Product
- BentoML
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
May 27, 2026BentoML is a Python library for building online serving systems optimized for AI apps and model inference.CVE-2026-44345 · Other software · bentoml · reported by GitHubHigh 8.8
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.39, src/bentoml/_internal/container/frontend/dockerfile/templates/base_v2.j2 interpolates docker.base_image raw with no escaping, newline filtering, or validation. A malicious bento.yaml with a multi-line docker.base_image value smuggles arbitrary Dockerfile directives into the generated Dockerfile, and bentoml containerize then runs docker build which executes the injected RUN directives on the victim host. This vulnerability is fixed in 1.4.39.
- Product
- BentoML
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
May 22, 2026BentoML is a Python library for building online serving systems optimized for AI apps and model inference.CVE-2026-40610 · Other software · bentoml · reported by GitHubMedium 5.5
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. In versions 1.4.38 and prior, the build packaging workflow follows attacker-controlled symlinks inside the build context and copies the referenced file contents into the generated Bento artifact. If a victim builds an untrusted repository or other attacker-supplied build context, the attacker can place a symlink such as loot.txt -> /tmp/outside-marker.txt or a link to a more sensitive local file. When bentoml build runs, BentoML dereferences the symlink and packages the target file contents into the Bento. The leaked file can then propagate further through export, push, or containerization workflows. An attacker can exfiltrate local files from the build host into the Bento artifact, exposing secrets such as cloud credentials, SSH keys, API tokens, environment files, or other sensitive local configurations. Because Bento artifacts are commonly exported, uploaded, stored, or containerized after build, the leaked file contents can spread beyond the original build machine. This issue has been fixed in version 1.4.39.
- Product
- BentoML
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
May 12, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-44223 · Other software · vllm-project · reported by GitHubMedium 6.5
vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
May 12, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-44222 · Other software · vllm-project · reported by GitHubMedium 6.5
vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
May 12, 2026The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization (CWE-502) in its model serving component.CVE-2026-31238 · Other software · reported by MITRECritical 9.8
The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization (CWE-502) in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load() without enabling the security-restrictive weights_only=True parameter. This default behavior allows the deserialization of arbitrary Python objects via the pickle module. An attacker can exploit this by providing a maliciously crafted PyTorch model file, leading to arbitrary code execution on the system hosting the Ludwig model server.
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
May 12, 2026webpack-dev-server versions up to and including 5.2.3 are vulnerable to cross-origin source code exposure when serving over a non-potentially trustworthy originCVE-2026-6402 · Other software · webpack-dev-server · reported by ce714d77-add3-4f53-aff5-83d477b104bbMedium 5.3
webpack-dev-server versions up to and including 5.2.3 are vulnerable to cross-origin source code exposure when serving over a non-potentially trustworthy origin such as plain HTTP. The previous fix relied on the Sec-Fetch-Mode and Sec-Fetch-Site request headers, which browsers omit for non-trustworthy origins, allowing a malicious site to load the bundled source as a script and read it across origins. Impact: an attacker controlling a website visited by a developer running webpack-dev-server can recover the application source code when the dev server runs over HTTP at a guessable host and port. Chromium based browsers from Chrome 142 onward are not affected due to local network access restrictions. Upgrade to webpack-dev-server 5.2.4 or later, which sets Cross-Origin-Resource-Policy: same-origin on responses.
- Product
- webpack-dev-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordcna.openjsf.orggithub.com
Apr 27, 2026NASA Earth Observing System Data and Information System (EOSDIS) MODAPS v8.1 was discovered to contain a SQL injection vulnerability in the category parameterCVE-2024-46636 · Other software · reported by MITRECritical 9.4
NASA Earth Observing System Data and Information System (EOSDIS) MODAPS v8.1 was discovered to contain a SQL injection vulnerability in the category parameter
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordbugcrowd.comgithub.com
Apr 20, 2026LMDeploy is a toolkit for compressing, deploying, and serving large language models.CVE-2026-33626 · Other software · InternLM · reported by GitHubHigh 7.5
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy's vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.
- Product
- lmdeploy
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Apr 6, 2026BentoML is a Python library for building online serving systems optimized for AI apps and model inference.CVE-2026-35044 · Other software · bentoml · reported by GitHubHigh 8.8
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.38, the Dockerfile generation function generate_containerfile() in src/bentoml/_internal/container/generate.py uses an unsandboxed jinja2.Environment with the jinja2.ext.do extension to render user-provided dockerfile_template files. When a victim imports a malicious bento archive and runs bentoml containerize, attacker-controlled Jinja2 template code executes arbitrary Python directly on the host machine, bypassing all container isolation. This vulnerability is fixed in 1.4.38.
- Product
- BentoML
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Apr 6, 2026BentoML is a Python library for building online serving systems optimized for AI apps and model inference.CVE-2026-35043 · Other software · bentoml · reported by GitHubHigh 7.8
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.38, the cloud deployment path in src/bentoml/_internal/cloud/deployment.py was not included in the fix for CVE-2026-33744. Line 1648 interpolates system_packages directly into a shell command using an f-string without any quoting. The generated script is uploaded to BentoCloud as setup.sh and executed on the cloud build infrastructure during deployment, making this a remote code execution on the CI/CD tier. This vulnerability is fixed in 1.4.38.
- Product
- BentoML
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Apr 6, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-34756 · Other software · vllm-project · reported by GitHubMedium 6.5
vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Apr 6, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-34755 · Other software · vllm-project · reported by GitHubMedium 6.5
vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comaccess.redhat.com
Apr 6, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-34753 · Other software · vllm-project · reported by GitHubMedium 5.4
vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side request forgery (SSRF) vulnerability in download_bytes_from_url allows any actor who can control batch input JSON to make the vLLM batch runner issue arbitrary HTTP/HTTPS requests from the server, without any URL validation or domain restrictions. This can be used to target internal services (e.g. cloud metadata endpoints or internal HTTP APIs) reachable from the vLLM host. This vulnerability is fixed in 0.19.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Apr 3, 2026** UNSUPPORTED WHEN ASSIGNED ** Focalboard version 8.0 fails to validate file ownership when serving uploaded files.CVE-2026-28736 · Other software · Mattermost · reported by responsibledisclosure@mattermost.comMedium 4.3
** UNSUPPORTED WHEN ASSIGNED ** Focalboard version 8.0 fails to validate file ownership when serving uploaded files. This allows an authenticated attacker who knows a victim's fileID to read the content of the file. NOTE: Focalboard as a standalone product is not maintained and no fix will be issued.
- Product
- Focalboard
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Apr 2, 2026vLLM is an inference and serving engine for large language models (LLMs).CVE-2026-34760 · Other software · vllm-project · reported by GitHubMedium 5.9
vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results in inconsistency between audio heard by humans (e.g., through headphones/regular speakers) and audio processed by AI models (Which infra via Librosa, such as vllm, transformer). This issue has been patched in version 0.18.0.
- Product
- vllm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Mar 31, 2026A command injection vulnerability exists in mlflow/mlflow when serving a model with `enable_mlserver=True`.CVE-2026-0596 · Other software · mlflow · reported by security@huntr.devHigh 7.8
A command injection vulnerability exists in mlflow/mlflow when serving a model with `enable_mlserver=True`. The `model_uri` is embedded directly into a shell command executed via `bash -c` without proper sanitization. If the `model_uri` contains shell metacharacters, such as `$()` or backticks, it allows for command substitution and execution of attacker-controlled commands. This vulnerability affects the latest version of mlflow/mlflow and can lead to privilege escalation if a higher-privileged service serves models from a directory writable by lower-privileged users.
- Product
- mlflow/mlflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Mar 30, 2026A command injection vulnerability exists in MLflow's model serving container initialization code, specifically in the `_install_model_dependencies_to_env()` funCVE-2025-15379 · Other software · mlflow · reported by security@huntr.devCritical 10
A command injection vulnerability exists in MLflow's model serving container initialization code, specifically in the `_install_model_dependencies_to_env()` function. When deploying a model with `env_manager=LOCAL`, MLflow reads dependency specifications from the model artifact's `python_env.yaml` file and directly interpolates them into a shell command without sanitization. This allows an attacker to supply a malicious model artifact and achieve arbitrary command execution on systems that deploy the model. The vulnerability affects versions 3.8.0 and is fixed in version 3.8.2.
- Product
- mlflow/mlflow
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Mar 26, 2026BentoML is a Python library for building online serving systems optimized for AI apps and model inference.CVE-2026-33744 · Other software · bentoml · reported by GitHubHigh 7.8
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.37, the `docker.system_packages` field in `bentofile.yaml` accepts arbitrary strings that are interpolated directly into Dockerfile `RUN` commands without sanitization. Since `system_packages` is semantically a list of OS package names (data), users do not expect values to be interpreted as shell commands. A malicious `bentofile.yaml` achieves arbitrary command execution during `bentoml containerize` / `docker build`. Version 1.4.37 fixes the issue.
- Product
- BentoML
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Where this comes from: the exploited list is CISA’s Known Exploited Vulnerabilities catalog. Everything else is the whole National Vulnerability Database, where each record is published by the team that found the bug (Wordfence, Patchstack, WPScan, the vendors themselves and others); we show who. Exploit odds are FIRST’s EPSS, updated daily. Titles and categories are ours, so check the linked record before acting on a detail. For a write-up of the big ones, see our advisories. Every vendor, and every WordPress plugin and theme with a recorded flaw, also has its own page. All of it is free to reuse as JSON, CSV or RSS.
Weekly security brief
The flaws that hit local websites, every Friday.
One short email: what got exploited this week, which WordPress plugins broke, and what to check. Unsubscribe in one click.
Tell us what you're building.
A website, your marketing, a security check, an app, or the thing you've been running out of a spreadsheet for three years. A few lines is plenty.
Not ready to talk yet? Run the free website check and see what Google sees.