Total
179 CVE
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-4729 | 1 Mozilla | 2 Firefox, Thunderbird | 2026-04-14 | 9.8 Critical |
| Memory safety bugs present in Firefox 148 and Thunderbird 148. Some of these bugs showed evidence of memory corruption and we presume that with enough effort some of these could have been exploited to run arbitrary code. This vulnerability was fixed in Firefox 149 and Thunderbird 149. | ||||
| CVE-2026-4721 | 1 Mozilla | 3 Firefox, Firefox Esr, Thunderbird | 2026-04-14 | 9.8 Critical |
| Memory safety bugs present in Firefox ESR 115.33, Firefox ESR 140.8, Thunderbird ESR 140.8, Firefox 148 and Thunderbird 148. Some of these bugs showed evidence of memory corruption and we presume that with enough effort some of these could have been exploited to run arbitrary code. This vulnerability was fixed in Firefox 149, Firefox ESR 115.34, Firefox ESR 140.9, Thunderbird 149, and Thunderbird 140.9. | ||||
| CVE-2026-5860 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-04-14 | 8.8 High |
| Use after free in WebRTC in Google Chrome prior to 147.0.7727.55 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High) | ||||
| CVE-2026-5861 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-04-14 | 8.8 High |
| Use after free in V8 in Google Chrome prior to 147.0.7727.55 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High) | ||||
| CVE-2026-5866 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-04-14 | 8.8 High |
| Use after free in Media in Google Chrome prior to 147.0.7727.55 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High) | ||||
| CVE-2026-5872 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-04-14 | 8.8 High |
| Use after free in Blink in Google Chrome prior to 147.0.7727.55 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High) | ||||
| CVE-2026-5874 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-04-14 | 9.6 Critical |
| Use after free in PrivateAI in Google Chrome prior to 147.0.7727.55 allowed a remote attacker who convinced a user to engage in specific UI gestures to potentially perform a sandbox escape via a crafted HTML page. (Chromium security severity: Medium) | ||||
| CVE-2026-5904 | 4 Apple, Google, Linux and 1 more | 4 Macos, Chrome, Linux Kernel and 1 more | 2026-04-14 | 8.8 High |
| Use after free in V8 in Google Chrome prior to 147.0.7727.55 allowed an attacker who convinced a user to install a malicious extension to potentially exploit heap corruption via a crafted Chrome Extension. (Chromium security severity: Low) | ||||
| CVE-2026-31426 | 1 Linux | 1 Linux Kernel | 2026-04-14 | 5.8 Medium |
| In the Linux kernel, the following vulnerability has been resolved: ACPI: EC: clean up handlers on probe failure in acpi_ec_setup() When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware platforms, it has already started the EC and installed the address space handler with the struct acpi_ec pointer as handler context. However, acpi_ec_setup() propagates the error without any cleanup. The caller acpi_ec_add() then frees the struct acpi_ec for non-boot instances, leaving a dangling handler context in ACPICA. Any subsequent AML evaluation that accesses an EC OpRegion field dispatches into acpi_ec_space_handler() with the freed pointer, causing a use-after-free: BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289) Write of size 8 at addr ffff88800721de38 by task init/1 Call Trace: <TASK> mutex_lock (kernel/locking/mutex.c:289) acpi_ec_space_handler (drivers/acpi/ec.c:1362) acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293) acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246) acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509) acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700) acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327) acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392) </TASK> Allocated by task 1: acpi_ec_alloc (drivers/acpi/ec.c:1424) acpi_ec_add (drivers/acpi/ec.c:1692) Freed by task 1: kfree (mm/slub.c:6876) acpi_ec_add (drivers/acpi/ec.c:1751) The bug triggers on reduced-hardware EC platforms (ec->gpe < 0) when the GPIO IRQ provider defers probing. Once the stale handler exists, any unprivileged sysfs read that causes AML to touch an EC OpRegion (battery, thermal, backlight) exercises the dangling pointer. Fix this by calling ec_remove_handlers() in the error path of acpi_ec_setup() before clearing first_ec. ec_remove_handlers() checks each EC_FLAGS_* bit before acting, so it is safe to call regardless of how far ec_install_handlers() progressed: -ENODEV (handler not installed): only calls acpi_ec_stop() -EPROBE_DEFER (handler installed): removes handler, stops EC | ||||
| CVE-2026-34757 | 1 Pnggroup | 1 Libpng | 2026-04-13 | 5.1 Medium |
| LIBPNG is a reference library for use in applications that read, create, and manipulate PNG (Portable Network Graphics) raster image files. From 1.0.9 to before 1.6.57, passing a pointer obtained from png_get_PLTE, png_get_tRNS, or png_get_hIST back into the corresponding setter on the same png_struct/png_info pair causes the setter to read from freed memory and copy its contents into the replacement buffer. The setter frees the internal buffer before copying from the caller-supplied pointer, which now dangles. The freed region may contain stale data (producing silently corrupted chunk metadata) or data from subsequent heap allocations (leaking unrelated heap contents into the chunk struct). This vulnerability is fixed in 1.6.57. | ||||
| CVE-2026-23471 | 1 Linux | 1 Linux Kernel | 2026-04-13 | 7.0 High |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. | ||||
| CVE-2026-31406 | 1 Linux | 1 Linux Kernel | 2026-04-13 | 5.5 Medium |
| 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-2026-31389 | 1 Linux | 1 Linux Kernel | 2026-04-13 | 4.7 Medium |
| In the Linux kernel, the following vulnerability has been resolved: spi: fix use-after-free on controller registration failure Make sure to deregister from driver core also in the unlikely event that per-cpu statistics allocation fails during controller registration to avoid use-after-free (of driver resources) and unclocked register accesses. | ||||
| CVE-2026-23416 | 1 Linux | 1 Linux Kernel | 2026-04-13 | N/A |
| In the Linux kernel, the following vulnerability has been resolved: mm/mseal: update VMA end correctly on merge Previously we stored the end of the current VMA in curr_end, and then upon iterating to the next VMA updated curr_start to curr_end to advance to the next VMA. However, this doesn't take into account the fact that a VMA might be updated due to a merge by vma_modify_flags(), which can result in curr_end being stale and thus, upon setting curr_start to curr_end, ending up with an incorrect curr_start on the next iteration. Resolve the issue by setting curr_end to vma->vm_end unconditionally to ensure this value remains updated should this occur. While we're here, eliminate this entire class of bug by simply setting const curr_[start/end] to be clamped to the input range and VMAs, which also happens to simplify the logic. | ||||
| CVE-2026-23393 | 1 Linux | 1 Linux Kernel | 2026-04-13 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: bridge: cfm: Fix race condition in peer_mep deletion When a peer MEP is being deleted, cancel_delayed_work_sync() is called on ccm_rx_dwork before freeing. However, br_cfm_frame_rx() runs in softirq context under rcu_read_lock (without RTNL) and can re-schedule ccm_rx_dwork via ccm_rx_timer_start() between cancel_delayed_work_sync() returning and kfree_rcu() being called. The following is a simple race scenario: cpu0 cpu1 mep_delete_implementation() cancel_delayed_work_sync(ccm_rx_dwork); br_cfm_frame_rx() // peer_mep still in hlist if (peer_mep->ccm_defect) ccm_rx_timer_start() queue_delayed_work(ccm_rx_dwork) hlist_del_rcu(&peer_mep->head); kfree_rcu(peer_mep, rcu); ccm_rx_work_expired() // on freed peer_mep To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync() in both peer MEP deletion paths, so that subsequent queue_delayed_work() calls from br_cfm_frame_rx() are silently rejected. The cc_peer_disable() helper retains cancel_delayed_work_sync() because it is also used for the CC enable/disable toggle path where the work must remain re-schedulable. | ||||
| CVE-2026-23392 | 1 Linux | 1 Linux Kernel | 2026-04-13 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: release flowtable after rcu grace period on error Call synchronize_rcu() after unregistering the hooks from error path, since a hook that already refers to this flowtable can be already registered, exposing this flowtable to packet path and nfnetlink_hook control plane. This error path is rare, it should only happen by reaching the maximum number hooks or by failing to set up to hardware offload, just call synchronize_rcu(). There is a check for already used device hooks by different flowtable that could result in EEXIST at this late stage. The hook parser can be updated to perform this check earlier to this error path really becomes rarely exercised. Uncovered by KASAN reported as use-after-free from nfnetlink_hook path when dumping hooks. | ||||
| CVE-2026-23344 | 1 Linux | 1 Linux Kernel | 2026-04-13 | N/A |
| In the Linux kernel, the following vulnerability has been resolved: crypto: ccp - Fix use-after-free on error path In the error path of sev_tsm_init_locked(), the code dereferences 't' after it has been freed with kfree(). The pr_err() statement attempts to access t->tio_en and t->tio_init_done after the memory has been released. Move the pr_err() call before kfree(t) to access the fields while the memory is still valid. This issue reported by Smatch static analyser | ||||
| CVE-2026-35094 | 3 Fedoraproject, Freedesktop, Redhat | 3 Fedora, Libinput, Enterprise Linux | 2026-04-08 | 3.3 Low |
| A flaw was found in libinput. An attacker capable of deploying a Lua plugin file in specific system directories can exploit a dangling pointer vulnerability. This occurs when a garbage collection cleanup function is called, leaving a pointer that can then be printed to system logs. This could potentially expose sensitive data if the memory location is re-used, leading to information disclosure. For this exploit to work, Lua plugins must be enabled in libinput and loaded by the compositor. | ||||
| CVE-2026-34764 | 1 Electron | 1 Electron | 2026-04-07 | 2.3 Low |
| Electron is a framework for writing cross-platform desktop applications using JavaScript, HTML and CSS. From 33.0.0-alpha.1 to before 39.8.5, 40.8.5, 41.1.0, and 42.0.0-alpha.5, apps that use offscreen rendering with GPU shared textures may be vulnerable to a use-after-free. Under certain conditions, the release() callback provided on a paint event texture can outlive its backing native state, and invoking it after that point dereferences freed memory in the main process, which may lead to a crash or memory corruption. Apps are only affected if they use offscreen rendering with webPreferences.offscreen: { useSharedTexture: true }. Apps that do not enable shared-texture offscreen rendering are not affected. To mitigate this issue, ensure texture.release() is called promptly after the texture has been consumed, before the texture object becomes unreachable. This vulnerability is fixed in 39.8.5, 40.8.5, 41.1.0, and 42.0.0-alpha.5. | ||||
| CVE-2026-33416 | 2 Libpng, Pnggroup | 2 Libpng, Libpng | 2026-04-03 | 7.5 High |
| LIBPNG is a reference library for use in applications that read, create, and manipulate PNG (Portable Network Graphics) raster image files. In versions 1.2.1 through 1.6.55, `png_set_tRNS` and `png_set_PLTE` each alias a heap-allocated buffer between `png_struct` and `png_info`, sharing a single allocation across two structs with independent lifetimes. The `trans_alpha` aliasing has been present since at least libpng 1.0, and the `palette` aliasing since at least 1.2.1. Both affect all prior release lines `png_set_tRNS` sets `png_ptr->trans_alpha = info_ptr->trans_alpha` (256-byte buffer) and `png_set_PLTE` sets `info_ptr->palette = png_ptr->palette` (768-byte buffer). In both cases, calling `png_free_data` (with `PNG_FREE_TRNS` or `PNG_FREE_PLTE`) frees the buffer through `info_ptr` while the corresponding `png_ptr` pointer remains dangling. Subsequent row-transform functions dereference and, in some code paths, write to the freed memory. A second call to `png_set_tRNS` or `png_set_PLTE` has the same effect, because both functions call `png_free_data` internally before reallocating the `info_ptr` buffer. Version 1.6.56 fixes the issue. | ||||