Export limit exceeded: 95264 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (95264 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-24213 | 1 Nvidia | 1 Triton Inference Server | 2026-05-20 | 8 High |
| NVIDIA Triton Inference Server contains a vulnerability in the DALI backend where an attacker could cause an out-of-bounds read. A successful exploit of this vulnerability might lead to code execution, data tampering, denial of service, or information disclosure. | ||||
| CVE-2026-6456 | 2 Beycanpress, Wordpress | 2 Account Switcher, Wordpress | 2026-05-20 | 8.8 High |
| The Account Switcher plugin for WordPress is vulnerable to Privilege Escalation in all versions up to, and including, 1.0.2. This is due to the `rememberLogin` REST API endpoint using a loose comparison (`!=` instead of `!==`) for secret validation at `app/RestAPI.php:111`, combined with no validation that the secret is non-empty. When a target user has never used the "Remember me" feature, their `asSecret` user meta does not exist, causing `get_user_meta()` to return an empty string. An attacker can send an empty `secret` parameter, which passes the comparison (`'' != ''` is `false`), and the endpoint then calls `wp_set_auth_cookie()` for the target user. Additionally, all REST routes use `permission_callback => '__return_true'` with no capability checks. This makes it possible for authenticated attackers, with Subscriber-level access and above, to switch to any user account including Administrator, ultimately granting themselves full administrative privileges. | ||||
| CVE-2026-24214 | 1 Nvidia | 1 Triton Inference Server | 2026-05-20 | 8 High |
| NVIDIA Triton Inference Server contains a vulnerability in the DALI backend where an attacker could cause an integer overflow. A successful exploit of this vulnerability might lead to code execution, data tampering, or denial of service. | ||||
| CVE-2026-34649 | 1 Adobe | 4 Adobe Commerce, Commerce, Commerce B2b and 1 more | 2026-05-20 | 7.5 High |
| Adobe Commerce versions 2.4.9-beta1, 2.4.8-p4, 2.4.7-p9, 2.4.6-p14, 2.4.5-p16, 2.4.4-p17 and earlier are affected by an Uncontrolled Resource Consumption vulnerability that could lead to application denial-of-service. An attacker could exploit this vulnerability to exhaust system resources, resulting in an application denial-of-service condition. Exploitation of this issue does not require user interaction. | ||||
| CVE-2026-34650 | 1 Adobe | 4 Adobe Commerce, Commerce, Commerce B2b and 1 more | 2026-05-20 | 7.5 High |
| Adobe Commerce versions 2.4.9-beta1, 2.4.8-p4, 2.4.7-p9, 2.4.6-p14, 2.4.5-p16, 2.4.4-p17 and earlier are affected by an Uncontrolled Resource Consumption vulnerability that could lead to application denial-of-service. An attacker could exploit this vulnerability to exhaust system resources, resulting in an application denial-of-service condition. Exploitation of this issue does not require user interaction. | ||||
| CVE-2026-34651 | 1 Adobe | 4 Adobe Commerce, Commerce, Commerce B2b and 1 more | 2026-05-20 | 7.5 High |
| Adobe Commerce versions 2.4.9-beta1, 2.4.8-p4, 2.4.7-p9, 2.4.6-p14, 2.4.5-p16, 2.4.4-p17 and earlier are affected by an Uncontrolled Resource Consumption vulnerability that could lead to application denial-of-service. An attacker could exploit this vulnerability to exhaust system resources, resulting in an application denial-of-service condition. Exploitation of this issue does not require user interaction. | ||||
| CVE-2026-34652 | 1 Adobe | 4 Adobe Commerce, Commerce, Commerce B2b and 1 more | 2026-05-20 | 7.5 High |
| Adobe Commerce versions 2.4.9-beta1, 2.4.8-p4, 2.4.7-p9, 2.4.6-p14, 2.4.5-p16, 2.4.4-p17 and earlier are affected by a Dependency on Vulnerable Third-Party Component vulnerability that could result in an application denial-of-service. An attacker could exploit this vulnerability to crash the application, leading to a denial-of-service condition. Exploitation of this issue does not require user interaction. | ||||
| CVE-2026-39250 | 1 Innoshop | 1 Innoshop | 2026-05-20 | 7.3 High |
| An authorization vulnerability exists in Innoshop 0.6.0. After logging into the frontend, an attacker can directly access backend application interfaces, leading to further dangerous operations. | ||||
| CVE-2026-31406 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| 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(). | ||||
| CVE-2026-43481 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: net-shapers: don't free reply skb after genlmsg_reply() genlmsg_reply() hands the reply skb to netlink, and netlink_unicast() consumes it on all return paths, whether the skb is queued successfully or freed on an error path. net_shaper_nl_get_doit() and net_shaper_nl_cap_get_doit() currently jump to free_msg after genlmsg_reply() fails and call nlmsg_free(msg), which can hit the same skb twice. Return the genlmsg_reply() error directly and keep free_msg only for pre-reply failures. | ||||
| CVE-2026-43380 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: hwmon: (pmbus/q54sj108a2) fix stack overflow in debugfs read The q54sj108a2_debugfs_read function suffers from a stack buffer overflow due to incorrect arguments passed to bin2hex(). The function currently passes 'data' as the destination and 'data_char' as the source. Because bin2hex() converts each input byte into two hex characters, a 32-byte block read results in 64 bytes of output. Since 'data' is only 34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end of the buffer onto the stack. Additionally, the arguments were swapped: it was reading from the zero-initialized 'data_char' and writing to 'data', resulting in all-zero output regardless of the actual I2C read. Fix this by: 1. Expanding 'data_char' to 66 bytes to safely hold the hex output. 2. Correcting the bin2hex() argument order and using the actual read count. 3. Using a pointer to select the correct output buffer for the final simple_read_from_buffer call. | ||||
| CVE-2026-34653 | 1 Adobe | 4 Adobe Commerce, Commerce, Commerce B2b and 1 more | 2026-05-20 | 8.7 High |
| Adobe Commerce versions 2.4.9-beta1, 2.4.8-p4, 2.4.7-p9, 2.4.6-p14, 2.4.5-p16, 2.4.4-p17 and earlier are affected by an Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') vulnerability that could result in arbitrary file system read and write. An authenticated attacker with administrative privileges could exploit this vulnerability to read or write files outside the restricted directory. Exploitation of this issue does not require user interaction. Scope is changed. | ||||
| CVE-2026-31069 | 1 Billabear | 1 Billabear | 2026-05-20 | 8.8 High |
| BillaBear (all versions prior to Jan 2026) contains a SQL Injection vulnerability in the EventRepository. User-controlled input from metric filter names and aggregation properties is directly interpolated into SQL queries using sprintf() without proper sanitization or identifier quoting. Although filter values are parameterized, the filter identifiers (keys) are not. An authenticated attacker with ROLE_ACCOUNT_MANAGER permissions can exploit this to execute arbitrary SQL commands. | ||||
| CVE-2026-31413 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: bpf: Fix unsound scalar forking in maybe_fork_scalars() for BPF_OR maybe_fork_scalars() is called for both BPF_AND and BPF_OR when the source operand is a constant. When dst has signed range [-1, 0], it forks the verifier state: the pushed path gets dst = 0, the current path gets dst = -1. For BPF_AND this is correct: 0 & K == 0. For BPF_OR this is wrong: 0 | K == K, not 0. The pushed path therefore tracks dst as 0 when the runtime value is K, producing an exploitable verifier/runtime divergence that allows out-of-bounds map access. Fix this by passing env->insn_idx (instead of env->insn_idx + 1) to push_stack(), so the pushed path re-executes the ALU instruction with dst = 0 and naturally computes the correct result for any opcode. | ||||
| CVE-2026-23461 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 8.8 High |
| In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user After commit ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in hci_chan_del"), l2cap_conn_del() uses conn->lock to protect access to conn->users. However, l2cap_register_user() and l2cap_unregister_user() don't use conn->lock, creating a race condition where these functions can access conn->users and conn->hchan concurrently with l2cap_conn_del(). This can lead to use-after-free and list corruption bugs, as reported by syzbot. Fix this by changing l2cap_register_user() and l2cap_unregister_user() to use conn->lock instead of hci_dev_lock(), ensuring consistent locking for the l2cap_conn structure. | ||||
| CVE-2026-23462 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 8.8 High |
| In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HIDP: Fix possible UAF This fixes the following trace caused by not dropping l2cap_conn reference when user->remove callback is called: [ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00 [ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy) [ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 97.809947] Call Trace: [ 97.809954] <TASK> [ 97.809961] dump_stack_lvl (lib/dump_stack.c:122) [ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808) [ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798) [ 97.810055] l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1)) [ 97.810086] ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341) [ 97.810117] hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2)) [ 97.810148] hci_dev_close_sync (net/bluetooth/hci_sync.c:5360) [ 97.810180] ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285) [ 97.810212] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810242] ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5)) [ 97.810267] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810290] ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752) [ 97.810320] hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716) [ 97.810346] vhci_release (drivers/bluetooth/hci_vhci.c:691) [ 97.810375] ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678) [ 97.810404] __fput (fs/file_table.c:470) [ 97.810430] task_work_run (kernel/task_work.c:235) [ 97.810451] ? __pfx_task_work_run (kernel/task_work.c:201) [ 97.810472] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810495] ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5)) [ 97.810527] do_exit (kernel/exit.c:972) [ 97.810547] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810574] ? __pfx_do_exit (kernel/exit.c:897) [ 97.810594] ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6)) [ 97.810616] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810639] ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4)) [ 97.810664] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810688] ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1)) [ 97.810721] do_group_exit (kernel/exit.c:1093) [ 97.810745] get_signal (kernel/signal.c:3007 (discriminator 1)) [ 97.810772] ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366) [ 97.810803] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810826] ? vfs_read (fs/read_write.c:555) [ 97.810854] ? __pfx_get_signal (kernel/signal.c:2800) [ 97.810880] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810905] ? __pfx_vfs_read (fs/read_write.c:555) [ 97.810932] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810960] arch_do_signal_or_restart (arch/ ---truncated--- | ||||
| CVE-2026-37530 | 2 Automotivelinux, Linuxfoundation | 2 Agl-service-can-low-level, Automotive Grade Linux | 2026-05-20 | 7.5 High |
| AGL agl-service-can-low-level thru 17.1.12 contains a stack buffer overflow in the uds-c library. The send_diagnostic_request function in uds.c allocates a 6-byte stack buffer (MAX_DIAGNOSTIC_PAYLOAD_SIZE=6) but copies up to 7 bytes (MAX_UDS_REQUEST_PAYLOAD_LENGTH=7) via memcpy at an offset of 1+pid_length (2-3 bytes), resulting in 1-4 bytes of controlled stack overflow. The payload_length field (uint8_t) has no bounds check against the destination buffer. On 32-bit ARM automotive ECUs without stack canaries, this can lead to return address overwrite and RCE. | ||||
| CVE-2026-42468 | 1 Openvehicles | 3 Open Vehicle Monitoring System, Open Vehicle Monitoring System 3, Open Vehicle Monitoring System Firmware | 2026-05-20 | 8.8 High |
| Buffer overflow vulnerability in Open Vehicle Monitoring System 3 (OVMS3) 3.3.005. In canformat_pcap.cpp , the parser's phdr.len field is not properly validated, allowing remote attackers to cause a denial of service or possibly execute arbitrary code via crafted PCAP input. | ||||
| CVE-2026-42469 | 1 Openvehicles | 3 Open Vehicle Monitoring System, Open Vehicle Monitoring System 3, Open Vehicle Monitoring System Firmware | 2026-05-20 | 8.6 High |
| Buffer overflow vulnerability in Open Vehicle Monitoring System 3 (OVMS3) 3.3.005. In canformat_canswitch.cpp the parser does not properly validate a CANswitch DLC value, allowing remote attackers to cause a denial of service or possibly execute arbitrary code via crafted CANswitch frames. | ||||
| CVE-2026-23466 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: drm/xe: Open-code GGTT MMIO access protection GGTT MMIO access is currently protected by hotplug (drm_dev_enter), which works correctly when the driver loads successfully and is later unbound or unloaded. However, if driver load fails, this protection is insufficient because drm_dev_unplug() is never called. Additionally, devm release functions cannot guarantee that all BOs with GGTT mappings are destroyed before the GGTT MMIO region is removed, as some BOs may be freed asynchronously by worker threads. To address this, introduce an open-coded flag, protected by the GGTT lock, that guards GGTT MMIO access. The flag is cleared during the dev_fini_ggtt devm release function to ensure MMIO access is disabled once teardown begins. (cherry picked from commit 4f3a998a173b4325c2efd90bdadc6ccd3ad9a431) | ||||