CVEs

Ferret is a declarative system for working with web data. Prior to 2.0.0-alpha.4, a path traversal vulnerability in Ferret's IO::FS::WRITE standard library function allows a malicious website to write arbitrary files to the filesystem of the machine running Ferret. When an operator scrapes a website that returns filenames containing ../ sequences, and uses those filenames to construct output paths (a standard scraping pattern), the attacker controls both the destination path and the file content. This can lead to remote code execution via cron jobs, SSH authorized_keys, shell profiles, or web shells. This vulnerability is fixed in 2.0.0-alpha.4.

A security vulnerability has been detected in code-projects Online FIR System 1.0. Affected by this vulnerability is an unknown functionality of the file /Login/checklogin.php of the component Login. The manipulation of the argument email/password leads to sql injection. The attack is possible to be carried out remotely. The exploit has been disclosed publicly and may be used.

Vim is an open source, command line text editor. Prior to version 9.2.0276, a modeline sandbox bypass in Vim allows arbitrary OS command execution when a user opens a crafted file. The `complete`, `guitabtooltip` and `printheader` options are missing the `P_MLE` flag, allowing a modeline to be executed. Additionally, the `mapset()` function lacks a `check_secure()` call, allowing it to be abused from sandboxed expressions. Commit 9.2.0276 fixes the issue.

Nhost is an open source Firebase alternative with GraphQL. Prior to 0.48.0, the auth service's OAuth provider callback flow places the refresh token directly into the redirect URL as a query parameter. Refresh tokens in URLs are logged in browser history, server access logs, HTTP Referer headers, and proxy/CDN logs. Note that the refresh token is one-time use and all of these leak vectors are on owned infrastructure or services integrated by the application developer. This vulnerability is fixed in 0.48.0.

KubeAI is an AI inference operator for kubernetes. Prior to 0.23.2, the ollamaStartupProbeScript() function in internal/modelcontroller/engine_ollama.go constructs a shell command string using fmt.Sprintf with unsanitized model URL components (ref, modelParam). This shell command is executed via bash -c as a Kubernetes startup probe. An attacker who can create or update Model custom resources can inject arbitrary shell commands that execute inside model server pods. This vulnerability is fixed in 0.23.2.

OpenEXR provides the specification and reference implementation of the EXR file format, an image storage format for the motion picture industry. From 3.1.0 to before 3.2.7, 3.3.9, and 3.4.9, internal_exr_undo_piz() advances the working wavelet pointer with signed 32-bit arithmetic. Because nx, ny, and wcount are int, a crafted EXR file can make this product overflow and wrap. The next channel then decodes from an incorrect address. The wavelet decode path operates in place, so this yields both out-of-bounds reads and out-of-bounds writes. This vulnerability is fixed in 3.2.7, 3.3.9, and 3.4.9.

OpenEXR provides the specification and reference implementation of the EXR file format, an image storage format for the motion picture industry. From 3.2.0 to before 3.2.7, 3.3.9, and 3.4.9, a misaligned memory write vulnerability exists in LossyDctDecoder_execute() in src/lib/OpenEXRCore/internal_dwa_decoder.h:749. When decoding a DWA or DWAB-compressed EXR file containing a FLOAT-type channel, the decoder performs an in-place HALF→FLOAT conversion by casting an unaligned uint8_t * row pointer to float * and writing through it. Because the row buffer may not be 4-byte aligned, this constitutes undefined behavior under the C standard and crashes immediately on architectures that enforce alignment (ARM, RISC-V, etc.). On x86 it is silently tolerated at runtime but remains exploitable via compiler optimizations that assume aligned access. This vulnerability is fixed in 3.2.7, 3.3.9, and 3.4.9.

SandboxJS is a JavaScript sandboxing library. Prior to 0.8.36, a scope modification vulnerability exists in @nyariv/sandboxjs. The vulnerability allows untrusted sandboxed code to leak internal interpreter objects through the new operator, exposing sandbox scope objects in the scope hierarchy to untrusted code; an unexpected and undesired exploit. While this could allow modifying scopes inside the sandbox, code evaluation remains sandboxed and prototypes remain protected throughout the execution. This vulnerability is fixed in 0.8.36.

SandboxJS is a JavaScript sandboxing library. Prior to 0.8.36, the @nyariv/sandboxjs parser contains unbounded recursion in the restOfExp function and the lispify/lispifyExpr call chain. An attacker can crash any Node.js process that parses untrusted input by supplying deeply nested expressions (e.g., ~2000 nested parentheses), causing a RangeError: Maximum call stack size exceeded that terminates the process. This vulnerability is fixed in 0.8.36.

Fedify is a TypeScript library for building federated server apps powered by ActivityPub. Prior to 1.9.6, 1.10.5, 2.0.8, and 2.1.1, @fedify/fedify follows HTTP redirects recursively in its remote document loader and authenticated document loader without enforcing a maximum redirect count or visited-URL loop detection. An attacker who controls a remote ActivityPub key or actor URL can force a server using Fedify to make repeated outbound requests from a single inbound request, leading to resource consumption and denial of service. This vulnerability is fixed in 1.9.6, 1.10.5, 2.0.8, and 2.1.1.

curl_cffi is the a Python binding for curl. Prior to 0.15.0, curl_cffi does not restrict requests to internal IP ranges, and follows redirects automatically via the underlying libcurl. Because of this, an attacker-controlled URL can redirect requests to internal services such as cloud metadata endpoints. In addition, curl_cffi’s TLS impersonation feature can make these requests appear as legitimate browser traffic, which may bypass certain network controls. This vulnerability is fixed in 0.15.0.

Memory Corruption when handling power management requests with improperly sized input/output buffers.

Transient DOS when receiving a service data frame with excessive length during device matching over a neighborhood awareness network protocol connection.

Memory Corruption when using deprecated DMABUF IOCTL calls to manage video memory.

Memory Corruption when accessing an output buffer without validating its size during IOCTL processing in a camera sensor driver.

Memory Corruption when accessing an output buffer without validating its size during IOCTL processing in a camera sensor driver.

Memory Corruption when accessing an output buffer without validating its size during IOCTL processing.

Memory Corruption when processing auxiliary sensor input/output control commands with insufficient buffer size validation.

Memory Corruption when accessing an output buffer without validating its size during IOCTL processing.

Memory Corruption when sending IOCTL requests with invalid buffer sizes during memcpy operations.

Memory Corruption when retrieving output buffer with insufficient size validation.

Transient DOS when processing nonstandard FILS Discovery Frames with out-of-range action sizes during initial scans.

Cryptographic issue while copying data to a destination buffer without validating its size.

Memory corruption when decoding corrupted satellite data files with invalid signature offsets.

Memory corruption while processing a frame request from user.

Memory corruption while preprocessing IOCTL request in JPEG driver.

Memory corruption when buffer copy operation fails due to integer overflow during attestation report generation.

Twitch Studio version 0.114.8 and prior contain a privilege escalation vulnerability in its privileged helper tool that allows local attackers to execute arbitrary code as root by exploiting an unprotected XPC service. Attackers can invoke the installFromPath:toPath:withReply: method to overwrite system files and privileged binaries, achieving full system compromise. Twitch Studio was discontinued in May 2024.

A security flaw has been discovered in OFFIS DCMTK up to 3.7.0. This impacts the function executeOnReception/executeOnEndOfStudy of the file dcmnet/apps/storescp.cc of the component storescp. Performing a manipulation results in os command injection. Remote exploitation of the attack is possible. The patch is named edbb085e45788dccaf0e64d71534cfca925784b8. Applying a patch is the recommended action to fix this issue.

Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') vulnerability in David Lingren Media LIbrary Assistant allows SQL Injection.This issue affects Media LIbrary Assistant: from n/a through 3.34.

Distribution is a toolkit to pack, ship, store, and deliver container content. Prior to 3.1.0, in pull-through cache mode, distribution discovers token auth endpoints by parsing WWW-Authenticate challenges returned by the configured upstream registry. The realm URL from a bearer challenge is used without validating that it matches the upstream registry host. As a result, an attacker-controlled upstream (or an attacker with MitM position to the upstream) can cause distribution to send the configured upstream credentials via basic auth to an attacker-controlled realm URL. This vulnerability is fixed in 3.1.0.

Homarr is an open-source dashboard. Prior to 1.57.0, a DOM-based Cross-Site Scripting (XSS) vulnerability has been discovered in Homarr's /auth/login page. The application improperly trusts a URL parameter (callbackUrl), which is passed to redirect and router.push. An attacker can craft a malicious link that, when opened by an authenticated user, performs a client-side redirect and executes arbitrary JavaScript in the context of their browser. This could lead to credential theft, internal network pivoting, and unauthorized actions performed on behalf of the victim. This vulnerability is fixed in 1.57.0.

GLPI is a free asset and IT management software package. From 10.0.0 to before 10.0.24 and 11.0.6, an authenticated user can perform a SQL injection via the logs export feature. This vulnerability is fixed in 10.0.24 and 11.0.6.

GLPI is a free asset and IT management software package. From 11.0.0 to before 11.0.6, an unauthenticated time-based blind SQL injection exists in GLPI's Search engine. This vulnerability is fixed in 11.0.6.

GLPI is a free asset and IT management software package. From 11.0.0 to before 11.0.6, an unauthenticated user can store an XSS payload through the inventory endpoint. This vulnerability is fixed in 11.0.6.

GLPI is a Free Asset and IT Management Software package. From 0.60 to before 10.0.24, an authenticated technician user can store an XSS payload in a supplier fields. This vulnerability is fixed in 10.0.24.

OpenAirInterface V2.2.0 AMF crashes when it receives an NGAP message with invalid procedure code or invalid PDU-type. For example when the message specification requires InitiatingMessage but sent with successfulOutcome.

Mattermost Plugin Legal Hold versions <=1.1.4 fail to halt request processing after a failed authorization check in ServeHTTP which allows an authenticated attacker to access, create, download, and delete legal hold data via crafted API requests to the plugin's endpoints. Mattermost Advisory ID: MMSA-2026-00621

A flaw has been found in code-projects Simple Laundry System 1.0. This vulnerability affects unknown code of the file /userfinishregister.php of the component Parameter Handler. This manipulation of the argument firstName causes sql injection. Remote exploitation of the attack is possible. The exploit has been published and may be used.

A security vulnerability has been detected in code-projects Easy Blog Site 1.0. Affected by this issue is some unknown functionality of the file login.php. The manipulation of the argument username/password leads to sql injection. The attack may be initiated remotely. The exploit has been disclosed publicly and may be used.

A weakness has been identified in projectworlds Car Rental System 1.0. Affected by this vulnerability is an unknown functionality of the file /pay.php of the component Parameter Handler. Executing a manipulation of the argument mpesa can lead to sql injection. The attack can be launched remotely. The exploit has been made available to the public and could be used for attacks.

A vulnerability was determined in Cyber-III Student-Management-System up to 1a938fa61e9f735078e9b291d2e6215b4942af3f. This affects an unknown function of the file /viva/update.php of the component HTTP POST Request Handler. This manipulation of the argument Name causes improper authorization. It is possible to initiate the attack remotely. The exploit has been publicly disclosed and may be utilized. This product is using a rolling release to provide continious delivery. Therefore, no version details for affected nor updated releases are available. The project was informed of the problem early through an issue report but has not responded yet.

A security vulnerability has been detected in projectworlds Car Rental System 1.0. This vulnerability affects unknown code of the file /message_admin.php of the component Parameter Handler. Such manipulation of the argument Message leads to sql injection. The attack may be launched remotely. The exploit has been disclosed publicly and may be used.

A vulnerability was identified in projectworlds Car Rental Project 1.0. Affected by this vulnerability is an unknown functionality of the file /book_car.php of the component Parameter Handler. The manipulation of the argument fname leads to sql injection. The attack can be initiated remotely. The exploit is publicly available and might be used.

A vulnerability was determined in assafelovic gpt-researcher up to 3.4.3. Affected is an unknown function of the component ws Endpoint. Executing a manipulation of the argument source_urls can lead to server-side request forgery. It is possible to launch the attack remotely. The exploit has been publicly disclosed and may be utilized. The project was informed of the problem early through an issue report but has not responded yet.

In the Linux kernel, the following vulnerability has been resolved: ksmbd: unset conn->binding on failed binding request When a multichannel SMB2_SESSION_SETUP request with SMB2_SESSION_REQ_FLAG_BINDING fails ksmbd sets conn->binding = true but never clears it on the error path. This leaves the connection in a binding state where all subsequent ksmbd_session_lookup_all() calls fall back to the global sessions table. This fix it by clearing conn->binding = false in the error path.

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately releases the lock without holding a reference to the socket. A concurrent close() can free the socket between the lock release and the subsequent sk->sk_state access, resulting in a use-after-free. Other functions in the same file (sco_sock_timeout(), sco_conn_del()) correctly use sco_sock_hold() to safely hold a reference under the lock. Fix by using sco_sock_hold() to take a reference before releasing the lock, and adding sock_put() on all exit paths.

In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink. These attributes are used by the kernel without any validation. Extend the netlink policies accordingly. Quoting the reporter: nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE value directly to ct->proto.sctp.state without checking that it is within the valid range. [..] and: ... with exp->dir = 100, the access at ct->master->tuplehash[100] reads 5600 bytes past the start of a 320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by UBSAN.

In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delayed_work_sync() is called from xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining states via __xfrm_state_delete(), which calls xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work. The following is a simple race scenario: cpu0 cpu1 cleanup_net() [Round 1] ops_undo_list() xfrm_net_exit() xfrm_nat_keepalive_net_fini() cancel_delayed_work_sync(nat_keepalive_work); xfrm_state_fini() xfrm_state_flush() xfrm_state_delete(x) __xfrm_state_delete(x) xfrm_nat_keepalive_state_updated(x) schedule_delayed_work(nat_keepalive_work); rcu_barrier(); net_complete_free(); net_passive_dec(net); llist_add(&net->defer_free_list, &defer_free_list); cleanup_net() [Round 2] rcu_barrier(); net_complete_free() kmem_cache_free(net_cachep, net); nat_keepalive_work() // on freed net To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().

A vulnerability was found in assafelovic gpt-researcher up to 3.4.3. This impacts an unknown function of the component HTTP REST API Endpoint. Performing a manipulation results in missing authentication. It is possible to initiate the attack remotely. The exploit has been made public and could be used. The project was informed of the problem early through an issue report but has not responded yet.