| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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. |
| In the Linux kernel, the following vulnerability has been resolved:
net: mana: fix use-after-free in mana_hwc_destroy_channel() by reordering teardown
A potential race condition exists in mana_hwc_destroy_channel() where
hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and
Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt
handler to dereference freed memory, leading to a use-after-free or
NULL pointer dereference in mana_hwc_handle_resp().
mana_smc_teardown_hwc() signals the hardware to stop but does not
synchronize against IRQ handlers already executing on other CPUs. The
IRQ synchronization only happens in mana_hwc_destroy_cq() via
mana_gd_destroy_eq() -> mana_gd_deregister_irq(). Since this runs
after kfree(hwc->caller_ctx), a concurrent mana_hwc_rx_event_handler()
can dereference freed caller_ctx (and rxq->msg_buf) in
mana_hwc_handle_resp().
Fix this by reordering teardown to reverse-of-creation order: destroy
the TX/RX work queues and CQ/EQ before freeing hwc->caller_ctx. This
ensures all in-flight interrupt handlers complete before the memory they
access is freed. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix use-after-free of share_conf in compound request
smb2_get_ksmbd_tcon() reuses work->tcon in compound requests without
validating tcon->t_state. ksmbd_tree_conn_lookup() checks t_state ==
TREE_CONNECTED on the initial lookup path, but the compound reuse path
bypasses this check entirely.
If a prior command in the compound (SMB2_TREE_DISCONNECT) sets t_state
to TREE_DISCONNECTED and frees share_conf via ksmbd_share_config_put(),
subsequent commands dereference the freed share_conf through
work->tcon->share_conf.
KASAN report:
[ 4.144653] ==================================================================
[ 4.145059] BUG: KASAN: slab-use-after-free in smb2_write+0xc74/0xe70
[ 4.145415] Read of size 4 at addr ffff88810430c194 by task kworker/1:1/44
[ 4.145772]
[ 4.145867] CPU: 1 UID: 0 PID: 44 Comm: kworker/1:1 Not tainted 7.0.0-rc3+ #60 PREEMPTLAZY
[ 4.145871] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[ 4.145875] Workqueue: ksmbd-io handle_ksmbd_work
[ 4.145888] Call Trace:
[ 4.145892] <TASK>
[ 4.145894] dump_stack_lvl+0x64/0x80
[ 4.145910] print_report+0xce/0x660
[ 4.145919] ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[ 4.145928] ? smb2_write+0xc74/0xe70
[ 4.145931] kasan_report+0xce/0x100
[ 4.145934] ? smb2_write+0xc74/0xe70
[ 4.145937] smb2_write+0xc74/0xe70
[ 4.145939] ? __pfx_smb2_write+0x10/0x10
[ 4.145942] ? _raw_spin_unlock+0xe/0x30
[ 4.145945] ? ksmbd_smb2_check_message+0xeb2/0x24c0
[ 4.145948] ? smb2_tree_disconnect+0x31c/0x480
[ 4.145951] handle_ksmbd_work+0x40f/0x1080
[ 4.145953] process_one_work+0x5fa/0xef0
[ 4.145962] ? assign_work+0x122/0x3e0
[ 4.145964] worker_thread+0x54b/0xf70
[ 4.145967] ? __pfx_worker_thread+0x10/0x10
[ 4.145970] kthread+0x346/0x470
[ 4.145976] ? recalc_sigpending+0x19b/0x230
[ 4.145980] ? __pfx_kthread+0x10/0x10
[ 4.145984] ret_from_fork+0x4fb/0x6c0
[ 4.145992] ? __pfx_ret_from_fork+0x10/0x10
[ 4.145995] ? __switch_to+0x36c/0xbe0
[ 4.145999] ? __pfx_kthread+0x10/0x10
[ 4.146003] ret_from_fork_asm+0x1a/0x30
[ 4.146013] </TASK>
[ 4.146014]
[ 4.149858] Allocated by task 44:
[ 4.149953] kasan_save_stack+0x33/0x60
[ 4.150061] kasan_save_track+0x14/0x30
[ 4.150169] __kasan_kmalloc+0x8f/0xa0
[ 4.150274] ksmbd_share_config_get+0x1dd/0xdd0
[ 4.150401] ksmbd_tree_conn_connect+0x7e/0x600
[ 4.150529] smb2_tree_connect+0x2e6/0x1000
[ 4.150645] handle_ksmbd_work+0x40f/0x1080
[ 4.150761] process_one_work+0x5fa/0xef0
[ 4.150873] worker_thread+0x54b/0xf70
[ 4.150978] kthread+0x346/0x470
[ 4.151071] ret_from_fork+0x4fb/0x6c0
[ 4.151176] ret_from_fork_asm+0x1a/0x30
[ 4.151286]
[ 4.151332] Freed by task 44:
[ 4.151418] kasan_save_stack+0x33/0x60
[ 4.151526] kasan_save_track+0x14/0x30
[ 4.151634] kasan_save_free_info+0x3b/0x60
[ 4.151751] __kasan_slab_free+0x43/0x70
[ 4.151861] kfree+0x1ca/0x430
[ 4.151952] __ksmbd_tree_conn_disconnect+0xc8/0x190
[ 4.152088] smb2_tree_disconnect+0x1cd/0x480
[ 4.152211] handle_ksmbd_work+0x40f/0x1080
[ 4.152326] process_one_work+0x5fa/0xef0
[ 4.152438] worker_thread+0x54b/0xf70
[ 4.152545] kthread+0x346/0x470
[ 4.152638] ret_from_fork+0x4fb/0x6c0
[ 4.152743] ret_from_fork_asm+0x1a/0x30
[ 4.152853]
[ 4.152900] The buggy address belongs to the object at ffff88810430c180
[ 4.152900] which belongs to the cache kmalloc-96 of size 96
[ 4.153226] The buggy address is located 20 bytes inside of
[ 4.153226] freed 96-byte region [ffff88810430c180, ffff88810430c1e0)
[ 4.153549]
[ 4.153596] The buggy address belongs to the physical page:
[ 4.153750] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88810430ce80 pfn:0x10430c
[ 4.154000] flags: 0x
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
drm: Fix use-after-free on framebuffers and property blobs when calling drm_dev_unplug
When trying to do a rather aggressive test of igt's "xe_module_load
--r reload" with a full desktop environment and game running I noticed
a few OOPSes when dereferencing freed pointers, related to
framebuffers and property blobs after the compositor exits.
Solve this by guarding the freeing in drm_file with drm_dev_enter/exit,
and immediately put the references from struct drm_file objects during
drm_dev_unplug().
Related warnings for framebuffers on the subtest:
[ 739.713076] ------------[ cut here ]------------
WARN_ON(!list_empty(&dev->mode_config.fb_list))
[ 739.713079] WARNING: drivers/gpu/drm/drm_mode_config.c:584 at drm_mode_config_cleanup+0x30b/0x320 [drm], CPU#12: xe_module_load/13145
....
[ 739.713328] Call Trace:
[ 739.713330] <TASK>
[ 739.713335] ? intel_pmdemand_destroy_state+0x11/0x20 [xe]
[ 739.713574] ? intel_atomic_global_obj_cleanup+0xe4/0x1a0 [xe]
[ 739.713794] intel_display_driver_remove_noirq+0x51/0xb0 [xe]
[ 739.714041] xe_display_fini_early+0x33/0x50 [xe]
[ 739.714284] devm_action_release+0xf/0x20
[ 739.714294] devres_release_all+0xad/0xf0
[ 739.714301] device_unbind_cleanup+0x12/0xa0
[ 739.714305] device_release_driver_internal+0x1b7/0x210
[ 739.714311] device_driver_detach+0x14/0x20
[ 739.714315] unbind_store+0xa6/0xb0
[ 739.714319] drv_attr_store+0x21/0x30
[ 739.714322] sysfs_kf_write+0x48/0x60
[ 739.714328] kernfs_fop_write_iter+0x16b/0x240
[ 739.714333] vfs_write+0x266/0x520
[ 739.714341] ksys_write+0x72/0xe0
[ 739.714345] __x64_sys_write+0x19/0x20
[ 739.714347] x64_sys_call+0xa15/0xa30
[ 739.714355] do_syscall_64+0xd8/0xab0
[ 739.714361] entry_SYSCALL_64_after_hwframe+0x4b/0x53
and
[ 739.714459] ------------[ cut here ]------------
[ 739.714461] xe 0000:67:00.0: [drm] drm_WARN_ON(!list_empty(&fb->filp_head))
[ 739.714464] WARNING: drivers/gpu/drm/drm_framebuffer.c:833 at drm_framebuffer_free+0x6c/0x90 [drm], CPU#12: xe_module_load/13145
[ 739.714715] RIP: 0010:drm_framebuffer_free+0x7a/0x90 [drm]
...
[ 739.714869] Call Trace:
[ 739.714871] <TASK>
[ 739.714876] drm_mode_config_cleanup+0x26a/0x320 [drm]
[ 739.714998] ? __drm_printfn_seq_file+0x20/0x20 [drm]
[ 739.715115] ? drm_mode_config_cleanup+0x207/0x320 [drm]
[ 739.715235] intel_display_driver_remove_noirq+0x51/0xb0 [xe]
[ 739.715576] xe_display_fini_early+0x33/0x50 [xe]
[ 739.715821] devm_action_release+0xf/0x20
[ 739.715828] devres_release_all+0xad/0xf0
[ 739.715843] device_unbind_cleanup+0x12/0xa0
[ 739.715850] device_release_driver_internal+0x1b7/0x210
[ 739.715856] device_driver_detach+0x14/0x20
[ 739.715860] unbind_store+0xa6/0xb0
[ 739.715865] drv_attr_store+0x21/0x30
[ 739.715868] sysfs_kf_write+0x48/0x60
[ 739.715873] kernfs_fop_write_iter+0x16b/0x240
[ 739.715878] vfs_write+0x266/0x520
[ 739.715886] ksys_write+0x72/0xe0
[ 739.715890] __x64_sys_write+0x19/0x20
[ 739.715893] x64_sys_call+0xa15/0xa30
[ 739.715900] do_syscall_64+0xd8/0xab0
[ 739.715905] entry_SYSCALL_64_after_hwframe+0x4b/0x53
and then finally file close blows up:
[ 743.186530] Oops: general protection fault, probably for non-canonical address 0xdead000000000122: 0000 [#1] SMP
[ 743.186535] CPU: 3 UID: 1000 PID: 3453 Comm: kwin_wayland Tainted: G W 7.0.0-rc1-valkyria+ #110 PREEMPT_{RT,(lazy)}
[ 743.186537] Tainted: [W]=WARN
[ 743.186538] Hardware name: Gigabyte Technology Co., Ltd. X299 AORUS Gaming 3/X299 AORUS Gaming 3-CF, BIOS F8n 12/06/2021
[ 743.186539] RIP: 0010:drm_framebuffer_cleanup+0x55/0xc0 [drm]
[ 743.186588] Code: d8 72 73 0f b6 42 05 ff c3 39 c3 72 e8 49 8d bd 50 07 00 00 31 f6 e8 3a 80 d3 e1 49 8b 44 24 10 49 8d 7c 24 08 49 8b 54 24 08 <48> 3b 38 0f 85 95 7f 02 00 48 3b 7a 08 0f 85 8b 7f 02 00 48 89 42
[ 743.186589] RSP: 0018:ffffc900085e3cf8 EFLAGS: 00
---truncated--- |
| Electron is a framework for writing cross-platform desktop applications using JavaScript, HTML and CSS. Prior to versions 38.8.6, 39.8.0, 40.7.0, and 41.0.0-beta.8, apps that allow downloads and programmatically destroy sessions may be vulnerable to a use-after-free. If a session is torn down while a native save-file dialog is open for a download, dismissing the dialog dereferences freed memory, which may lead to a crash or memory corruption. Apps that do not destroy sessions at runtime, or that do not permit downloads, are not affected. This issue has been patched in versions 38.8.6, 39.8.0, 40.7.0, and 41.0.0-beta.8. |
| 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(). |
| 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. |
| A use-after-free issue was addressed with improved memory management. This issue is fixed in Safari 26.2, iOS 18.7.3 and iPadOS 18.7.3, iOS 26.2 and iPadOS 26.2, macOS Tahoe 26.2, tvOS 26.2, visionOS 26.2, watchOS 26.2. Processing maliciously crafted web content may lead to arbitrary code execution. Apple is aware of a report that this issue may have been exploited in an extremely sophisticated attack against specific targeted individuals on versions of iOS before iOS 26. CVE-2025-14174 was also issued in response to this report. |
| 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. |
| A flaw was found in virtio-win, specifically within the VirtIO Block (BLK) device. When the device undergoes a reset, it fails to properly manage memory, resulting in a use-after-free vulnerability. This issue could allow a local attacker to corrupt system memory, potentially leading to system instability or unexpected behavior. |
| In the Linux kernel, the following vulnerability has been resolved:
wifi: cfg80211: cancel rfkill_block work in wiphy_unregister()
There is a use-after-free error in cfg80211_shutdown_all_interfaces found
by syzkaller:
BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220
Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326
CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
Workqueue: events cfg80211_rfkill_block_work
Call Trace:
<TASK>
dump_stack_lvl+0x116/0x1f0
print_report+0xcd/0x630
kasan_report+0xe0/0x110
cfg80211_shutdown_all_interfaces+0x213/0x220
cfg80211_rfkill_block_work+0x1e/0x30
process_one_work+0x9cf/0x1b70
worker_thread+0x6c8/0xf10
kthread+0x3c5/0x780
ret_from_fork+0x56d/0x700
ret_from_fork_asm+0x1a/0x30
</TASK>
The problem arises due to the rfkill_block work is not cancelled when wiphy
is being unregistered. In order to fix the issue cancel the corresponding
work in wiphy_unregister().
Found by Linux Verification Center (linuxtesting.org) with Syzkaller. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nft_set_pipapo: split gc into unlink and reclaim phase
Yiming Qian reports Use-after-free in the pipapo set type:
Under a large number of expired elements, commit-time GC can run for a very
long time in a non-preemptible context, triggering soft lockup warnings and
RCU stall reports (local denial of service).
We must split GC in an unlink and a reclaim phase.
We cannot queue elements for freeing until pointers have been swapped.
Expired elements are still exposed to both the packet path and userspace
dumpers via the live copy of the data structure.
call_rcu() does not protect us: dump operations or element lookups starting
after call_rcu has fired can still observe the free'd element, unless the
commit phase has made enough progress to swap the clone and live pointers
before any new reader has picked up the old version.
This a similar approach as done recently for the rbtree backend in commit
35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert"). |
| 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. |
| 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. |
| In the Linux kernel, the following vulnerability has been resolved:
apparmor: fix race between freeing data and fs accessing it
AppArmor was putting the reference to i_private data on its end after
removing the original entry from the file system. However the inode
can aand does live beyond that point and it is possible that some of
the fs call back functions will be invoked after the reference has
been put, which results in a race between freeing the data and
accessing it through the fs.
While the rawdata/loaddata is the most likely candidate to fail the
race, as it has the fewest references. If properly crafted it might be
possible to trigger a race for the other types stored in i_private.
Fix this by moving the put of i_private referenced data to the correct
place which is during inode eviction. |
| Use after free in Web MIDI in Google Chrome on Android prior to 146.0.7680.178 allowed a remote attacker to execute arbitrary code via a crafted HTML page. (Chromium security severity: High) |
| Use after free in WebCodecs in Google Chrome prior to 146.0.7680.178 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High) |
| Use after free in Dawn in Google Chrome prior to 146.0.7680.178 allowed a remote attacker who had compromised the renderer process to execute arbitrary code via a crafted HTML page. (Chromium security severity: High) |
| Use after free in Dawn in Google Chrome prior to 146.0.7680.178 allowed a remote attacker who had compromised the renderer process to execute arbitrary code via a crafted HTML page. (Chromium security severity: High) |
| Use after free in WebGL in Google Chrome prior to 146.0.7680.178 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High) |
