Export limit exceeded: 412849 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (36304 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-43461 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: spi: amlogic: spifc-a4: Fix DMA mapping error handling Fix three bugs in aml_sfc_dma_buffer_setup() error paths: 1. Unnecessary goto: When the first DMA mapping (sfc->daddr) fails, nothing needs cleanup. Use direct return instead of goto. 2. Double-unmap bug: When info DMA mapping failed, the code would unmap sfc->daddr inline, then fall through to out_map_data which would unmap it again, causing a double-unmap. 3. Wrong unmap size: The out_map_info label used datalen instead of infolen when unmapping sfc->iaddr, which could lead to incorrect DMA sync behavior. | ||||
| CVE-2026-43462 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.5 High |
| In the Linux kernel, the following vulnerability has been resolved: net: spacemit: Fix error handling in emac_tx_mem_map() The DMA mappings were leaked on mapping error. Free them with the existing emac_free_tx_buf() function. | ||||
| CVE-2026-43425 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: usb: image: mdc800: kill download URB on timeout mdc800_device_read() submits download_urb and waits for completion. If the timeout fires and the device has not responded, the function returns without killing the URB, leaving it active. A subsequent read() resubmits the same URB while it is still in-flight, triggering the WARN in usb_submit_urb(): "URB submitted while active" Check the return value of wait_event_timeout() and kill the URB if it indicates timeout, ensuring the URB is complete before its status is inspected or the URB is resubmitted. Similar to - commit 372c93131998 ("USB: yurex: fix control-URB timeout handling") - commit b98d5000c505 ("media: rc: iguanair: handle timeouts") | ||||
| CVE-2026-43476 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: iio: chemical: sps30_i2c: fix buffer size in sps30_i2c_read_meas() sizeof(num) evaluates to sizeof(size_t) (8 bytes on 64-bit) instead of the intended __be32 element size (4 bytes). Use sizeof(*meas) to correctly match the buffer element type. | ||||
| CVE-2026-43428 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: USB: core: Limit the length of unkillable synchronous timeouts The usb_control_msg(), usb_bulk_msg(), and usb_interrupt_msg() APIs in usbcore allow unlimited timeout durations. And since they use uninterruptible waits, this leaves open the possibility of hanging a task for an indefinitely long time, with no way to kill it short of unplugging the target device. To prevent this sort of problem, enforce a maximum limit on the length of these unkillable timeouts. The limit chosen here, somewhat arbitrarily, is 60 seconds. On many systems (although not all) this is short enough to avoid triggering the kernel's hung-task detector. In addition, clear up the ambiguity of negative timeout values by treating them the same as 0, i.e., using the maximum allowed timeout. | ||||
| CVE-2026-43429 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: USB: usbtmc: Use usb_bulk_msg_killable() with user-specified timeouts The usbtmc driver accepts timeout values specified by the user in an ioctl command, and uses these timeouts for some usb_bulk_msg() calls. Since the user can specify arbitrarily long timeouts and usb_bulk_msg() uses unkillable waits, call usb_bulk_msg_killable() instead to avoid the possibility of the user hanging a kernel thread indefinitely. | ||||
| CVE-2026-43454 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: Fix for duplicate device in netdev hooks When handling NETDEV_REGISTER notification, duplicate device registration must be avoided since the device may have been added by nft_netdev_hook_alloc() already when creating the hook. | ||||
| CVE-2026-43455 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: mctp: route: hold key->lock in mctp_flow_prepare_output() mctp_flow_prepare_output() checks key->dev and may call mctp_dev_set_key(), but it does not hold key->lock while doing so. mctp_dev_set_key() and mctp_dev_release_key() are annotated with __must_hold(&key->lock), so key->dev access is intended to be serialized by key->lock. The mctp_sendmsg() transmit path reaches mctp_flow_prepare_output() via mctp_local_output() -> mctp_dst_output() without holding key->lock, so the check-and-set sequence is racy. Example interleaving: CPU0 CPU1 ---- ---- mctp_flow_prepare_output(key, devA) if (!key->dev) // sees NULL mctp_flow_prepare_output( key, devB) if (!key->dev) // still NULL mctp_dev_set_key(devB, key) mctp_dev_hold(devB) key->dev = devB mctp_dev_set_key(devA, key) mctp_dev_hold(devA) key->dev = devA // overwrites devB Now both devA and devB references were acquired, but only the final key->dev value is tracked for release. One reference can be lost, causing a resource leak as mctp_dev_release_key() would only decrease the reference on one dev. Fix by taking key->lock around the key->dev check and mctp_dev_set_key() call. | ||||
| CVE-2026-8766 | 2 Kilo, Kilo-org | 3 Kilo Code, Kilo Code Cli, Kilocode | 2026-05-20 | 4.3 Medium |
| A flaw has been found in Kilo-Org kilocode up to 7.0.47. This issue affects the function Load of the file packages/opencode/src/config/config.ts of the component Environment Variable Handler. Executing a manipulation of the argument KILO_CONFIG_CONTENT can lead to information disclosure. It is possible to launch the attack remotely. The exploit has been published and may be used. The vendor was contacted early about this disclosure but did not respond in any way. | ||||
| 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-2026-23465 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: btrfs: log new dentries when logging parent dir of a conflicting inode If we log the parent directory of a conflicting inode, we are not logging the new dentries of the directory, so when we finish we have the parent directory's inode marked as logged but we did not log its new dentries. As a consequence if the parent directory is explicitly fsynced later and it does not have any new changes since we logged it, the fsync is a no-op and after a power failure the new dentries are missing. Example scenario: $ mkdir foo $ sync $rmdir foo $ mkdir dir1 $ mkdir dir2 # A file with the same name and parent as the directory we just deleted # and was persisted in a past transaction. So the deleted directory's # inode is a conflicting inode of this new file's inode. $ touch foo $ ln foo dir2/link # The fsync on dir2 will log the parent directory (".") because the # conflicting inode (deleted directory) does not exists anymore, but it # it does not log its new dentries (dir1). $ xfs_io -c "fsync" dir2 # This fsync on the parent directory is no-op, since the previous fsync # logged it (but without logging its new dentries). $ xfs_io -c "fsync" . <power failure> # After log replay dir1 is missing. Fix this by ensuring we log new dir dentries whenever we log the parent directory of a no longer existing conflicting inode. A test case for fstests will follow soon. | ||||
| CVE-2023-4993 | 1 Utarit | 2 Solipay Mobile, Solipay Mobile App | 2026-05-20 | 7.5 High |
| Incorrect Use of Privileged APIs vulnerability in Utarit Information Technologies SoliPay Mobile App allows Collect Data as Provided by Users. This issue affects SoliPay Mobile App: before 5.0.8. | ||||
| CVE-2023-26314 | 2 Debian, Mono-project | 2 Debian Linux, Mono | 2026-05-20 | 8.8 High |
| The mono package before 6.8.0.105+dfsg-3.3 for Debian allows arbitrary code execution because the application/x-ms-dos-executable MIME type is associated with an un-sandboxed Mono CLR interpreter. | ||||
| CVE-2026-4342 | 1 Kubernetes | 2 Ingress-nginx, Nginx Ingress Controller | 2026-05-19 | 8.8 High |
| A security issue was discovered in ingress-nginx where a combination of Ingress annotations can be used to inject configuration into nginx. This can lead to arbitrary code execution in the context of the ingress-nginx controller, and disclosure of Secrets accessible to the controller. (Note that in the default installation, the controller can access all Secrets cluster-wide.) | ||||
| CVE-2026-31439 | 1 Linux | 1 Linux Kernel | 2026-05-19 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: dmaengine: xilinx: xdma: Fix regmap init error handling devm_regmap_init_mmio returns an ERR_PTR() upon error, not NULL. Fix the error check and also fix the error message. Use the error code from ERR_PTR() instead of the wrong value in ret. | ||||
| CVE-2026-43092 | 1 Linux | 1 Linux Kernel | 2026-05-19 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: xsk: validate MTU against usable frame size on bind AF_XDP bind currently accepts zero-copy pool configurations without verifying that the device MTU fits into the usable frame space provided by the UMEM chunk. This becomes a problem since we started to respect tailroom which is subtracted from chunk_size (among with headroom). 2k chunk size might not provide enough space for standard 1500 MTU, so let us catch such settings at bind time. Furthermore, validate whether underlying HW will be able to satisfy configured MTU wrt XSK's frame size multiplied by supported Rx buffer chain length (that is exposed via net_device::xdp_zc_max_segs). | ||||
| CVE-2026-43095 | 1 Linux | 1 Linux Kernel | 2026-05-19 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: ASoC: SDCA: Fix errors in IRQ cleanup IRQs are enabled through sdca_irq_populate() from component probe using devm_request_threaded_irq(), this however means the IRQs can persist if the sound card is torn down. Some of the IRQ handlers store references to the card and the kcontrols which can then fail. Some detail of the crash was explained in [1]. Generally it is not advised to use devm outside of bus probe, so the code is updated to not use devm. The IRQ requests are not moved to bus probe time as it makes passing the snd_soc_component into the IRQs very awkward and would the require a second step once the component is available, so it is simpler to just register the IRQs at this point, even though that necessitates some manual cleanup. | ||||
| CVE-2026-31378 | 1 Apache | 1 Ofbiz | 2026-05-19 | 6.5 Medium |
| Improper Input Validation vulnerability in Apache OFBiz. This issue affects Apache OFBiz: before 24.09.06. Users are recommended to upgrade to version 24.09.06, which fixes the issue. | ||||
| CVE-2023-29335 | 1 Microsoft | 16 365 Apps, Office, Office Long Term Servicing Channel and 13 more | 2026-05-19 | 7.5 High |
| Microsoft Word Security Feature Bypass Vulnerability | ||||