Export limit exceeded: 35404 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (35404 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-43067 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 9.8 Critical |
| In the Linux kernel, the following vulnerability has been resolved: ext4: handle wraparound when searching for blocks for indirect mapped blocks Commit 4865c768b563 ("ext4: always allocate blocks only from groups inode can use") restricts what blocks will be allocated for indirect block based files to block numbers that fit within 32-bit block numbers. However, when using a review bot running on the latest Gemini LLM to check this commit when backporting into an LTS based kernel, it raised this concern: If ac->ac_g_ex.fe_group is >= ngroups (for instance, if the goal group was populated via stream allocation from s_mb_last_groups), then start will be >= ngroups. Does this allow allocating blocks beyond the 32-bit limit for indirect block mapped files? The commit message mentions that ext4_mb_scan_groups_linear() takes care to not select unsupported groups. However, its loop uses group = *start, and the very first iteration will call ext4_mb_scan_group() with this unsupported group because next_linear_group() is only called at the end of the iteration. After reviewing the code paths involved and considering the LLM review, I determined that this can happen when there is a file system where some files/directories are extent-mapped and others are indirect-block mapped. To address this, add a safety clamp in ext4_mb_scan_groups(). | ||||
| CVE-2026-31418 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: ipset: drop logically empty buckets in mtype_del mtype_del() counts empty slots below n->pos in k, but it only drops the bucket when both n->pos and k are zero. This misses buckets whose live entries have all been removed while n->pos still points past deleted slots. Treat a bucket as empty when all positions below n->pos are unused and release it directly instead of shrinking it further. | ||||
| CVE-2025-71239 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: audit: add fchmodat2() to change attributes class fchmodat2(), introduced in version 6.6 is currently not in the change attribute class of audit. Calling fchmodat2() to change a file attribute in the same fashion than chmod() or fchmodat() will bypass audit rules such as: -w /tmp/test -p rwa -k test_rwa The current patch adds fchmodat2() to the change attributes class. | ||||
| CVE-2025-31973 | 1 Hcltech | 1 Bigfix Service Management | 2026-05-20 | 4 Medium |
| HCL BigFix Service Management (SM) is susceptible to a Configuration – 'Insecure Use of Base Image Version'. Using outdated or insecure base images may introduce known vulnerabilities, potentially increasing the risk of exploitation in the application environment. | ||||
| CVE-2025-31985 | 1 Hcltech | 1 Bigfix Service Management | 2026-05-20 | 3.7 Low |
| HCL BigFix Service Management (SM) is affected by a security misconfiguration due to a missing or insecure “X-Content-Type-Options” header. This could allow browsers to perform MIME-type sniffing, potentially causing malicious content to be interpreted and executed incorrectly. | ||||
| 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-2026-43464 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.5 High |
| In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: RX, Fix XDP multi-buf frag counting for legacy RQ XDP multi-buf programs can modify the layout of the XDP buffer when the program calls bpf_xdp_pull_data() or bpf_xdp_adjust_tail(). The referenced commit in the fixes tag corrected the assumption in the mlx5 driver that the XDP buffer layout doesn't change during a program execution. However, this fix introduced another issue: the dropped fragments still need to be counted on the driver side to avoid page fragment reference counting issues. Such issue can be observed with the test_xdp_native_adjst_tail_shrnk_data selftest when using a payload of 3600 and shrinking by 256 bytes (an upcoming selftest patch): the last fragment gets released by the XDP code but doesn't get tracked by the driver. This results in a negative pp_ref_count during page release and the following splat: WARNING: include/net/page_pool/helpers.h:297 at mlx5e_page_release_fragmented.isra.0+0x4a/0x50 [mlx5_core], CPU#12: ip/3137 Modules linked in: [...] CPU: 12 UID: 0 PID: 3137 Comm: ip Not tainted 6.19.0-rc3+ #12 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:mlx5e_page_release_fragmented.isra.0+0x4a/0x50 [mlx5_core] [...] Call Trace: <TASK> mlx5e_dealloc_rx_wqe+0xcb/0x1a0 [mlx5_core] mlx5e_free_rx_descs+0x7f/0x110 [mlx5_core] mlx5e_close_rq+0x50/0x60 [mlx5_core] mlx5e_close_queues+0x36/0x2c0 [mlx5_core] mlx5e_close_channel+0x1c/0x50 [mlx5_core] mlx5e_close_channels+0x45/0x80 [mlx5_core] mlx5e_safe_switch_params+0x1a5/0x230 [mlx5_core] mlx5e_change_mtu+0xf3/0x2f0 [mlx5_core] netif_set_mtu_ext+0xf1/0x230 do_setlink.isra.0+0x219/0x1180 rtnl_newlink+0x79f/0xb60 rtnetlink_rcv_msg+0x213/0x3a0 netlink_rcv_skb+0x48/0xf0 netlink_unicast+0x24a/0x350 netlink_sendmsg+0x1ee/0x410 __sock_sendmsg+0x38/0x60 ____sys_sendmsg+0x232/0x280 ___sys_sendmsg+0x78/0xb0 __sys_sendmsg+0x5f/0xb0 [...] do_syscall_64+0x57/0xc50 This patch fixes the issue by doing page frag counting on all the original XDP buffer fragments for all relevant XDP actions (XDP_TX , XDP_REDIRECT and XDP_PASS). This is basically reverting to the original counting before the commit in the fixes tag. As frag_page is still pointing to the original tail, the nr_frags parameter to xdp_update_skb_frags_info() needs to be calculated in a different way to reflect the new nr_frags. | ||||
| 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-2026-43428 | 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-2026-31416 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: account for netlink header size This is a followup to an old bug fix: NLMSG_DONE needs to account for the netlink header size, not just the attribute size. This can result in a WARN splat + drop of the netlink message, but other than this there are no ill effects. | ||||
| CVE-2026-31414 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 9.8 Critical |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: use expect->helper Use expect->helper in ctnetlink and /proc to dump the helper name. Using nfct_help() without holding a reference to the master conntrack is unsafe. Use exp->master->helper in ctnetlink path if userspace does not provide an explicit helper when creating an expectation to retain the existing behaviour. The ctnetlink expectation path holds the reference on the master conntrack and nf_conntrack_expect lock and the nfnetlink glue path refers to the master ct that is attached to the skb. | ||||
| 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-2026-31409 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 8.8 High |
| 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. | ||||
| CVE-2026-31410 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 5.5 Medium |
| In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume identifier as the primary choice. For filesystems that do not provide a UUID, fall back to stfs.f_fsid obtained from vfs_statfs(). | ||||
| 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. | ||||