| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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) |
| 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) |
| 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) |
| 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) |
| 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 |
| Memory safety bugs present in Firefox 144 and Thunderbird 144. 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 145 and Thunderbird 145. |
| Use-after-free in the WebRTC: Audio/Video component. This vulnerability was fixed in Firefox 145, Firefox ESR 140.5, Thunderbird 145, and Thunderbird 140.5. |
| Use-after-free in the Audio/Video component. This vulnerability was fixed in Firefox 145, Firefox ESR 140.5, Firefox ESR 115.30, Thunderbird 145, and Thunderbird 140.5. |
| 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. |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
| 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:
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. |
| In the Linux kernel, the following vulnerability has been resolved:
net: shaper: protect late read accesses to the hierarchy
We look up a netdev during prep of Netlink ops (pre- callbacks)
and take a ref to it. Then later in the body of the callback
we take its lock or RCU which are the actual protections.
This is not proper, a conversion from a ref to a locked netdev
must include a liveness check (a check if the netdev hasn't been
unregistered already). Fix the read cases (those under RCU).
Writes needs a separate change to protect from creating the
hierarchy after flush has already run. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix use-after-free in durable v2 replay of active file handles
parse_durable_handle_context() unconditionally assigns dh_info->fp->conn
to the current connection when handling a DURABLE_REQ_V2 context with
SMB2_FLAGS_REPLAY_OPERATION. ksmbd_lookup_fd_cguid() does not filter by
fp->conn, so it returns file handles that are already actively connected.
The unconditional overwrite replaces fp->conn, and when the overwriting
connection is subsequently freed, __ksmbd_close_fd() dereferences the
stale fp->conn via spin_lock(&fp->conn->llist_lock), causing a
use-after-free.
KASAN report:
[ 7.349357] ==================================================================
[ 7.349607] BUG: KASAN: slab-use-after-free in _raw_spin_lock+0x75/0xe0
[ 7.349811] Write of size 4 at addr ffff8881056ac18c by task kworker/1:2/108
[ 7.350010]
[ 7.350064] CPU: 1 UID: 0 PID: 108 Comm: kworker/1:2 Not tainted 7.0.0-rc3+ #58 PREEMPTLAZY
[ 7.350068] 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
[ 7.350070] Workqueue: ksmbd-io handle_ksmbd_work
[ 7.350083] Call Trace:
[ 7.350087] <TASK>
[ 7.350087] dump_stack_lvl+0x64/0x80
[ 7.350094] print_report+0xce/0x660
[ 7.350100] ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[ 7.350101] ? __pfx___mod_timer+0x10/0x10
[ 7.350106] ? _raw_spin_lock+0x75/0xe0
[ 7.350108] kasan_report+0xce/0x100
[ 7.350109] ? _raw_spin_lock+0x75/0xe0
[ 7.350114] kasan_check_range+0x105/0x1b0
[ 7.350116] _raw_spin_lock+0x75/0xe0
[ 7.350118] ? __pfx__raw_spin_lock+0x10/0x10
[ 7.350119] ? __call_rcu_common.constprop.0+0x25e/0x780
[ 7.350125] ? close_id_del_oplock+0x2cc/0x4e0
[ 7.350128] __ksmbd_close_fd+0x27f/0xaf0
[ 7.350131] ksmbd_close_fd+0x135/0x1b0
[ 7.350133] smb2_close+0xb19/0x15b0
[ 7.350142] ? __pfx_smb2_close+0x10/0x10
[ 7.350143] ? xas_load+0x18/0x270
[ 7.350146] ? _raw_spin_lock+0x84/0xe0
[ 7.350148] ? __pfx__raw_spin_lock+0x10/0x10
[ 7.350150] ? _raw_spin_unlock+0xe/0x30
[ 7.350151] ? ksmbd_smb2_check_message+0xeb2/0x24c0
[ 7.350153] ? ksmbd_tree_conn_lookup+0xcd/0xf0
[ 7.350154] handle_ksmbd_work+0x40f/0x1080
[ 7.350156] process_one_work+0x5fa/0xef0
[ 7.350162] ? assign_work+0x122/0x3e0
[ 7.350163] worker_thread+0x54b/0xf70
[ 7.350165] ? __pfx_worker_thread+0x10/0x10
[ 7.350166] kthread+0x346/0x470
[ 7.350170] ? recalc_sigpending+0x19b/0x230
[ 7.350176] ? __pfx_kthread+0x10/0x10
[ 7.350178] ret_from_fork+0x4fb/0x6c0
[ 7.350183] ? __pfx_ret_from_fork+0x10/0x10
[ 7.350185] ? __switch_to+0x36c/0xbe0
[ 7.350188] ? __pfx_kthread+0x10/0x10
[ 7.350190] ret_from_fork_asm+0x1a/0x30
[ 7.350197] </TASK>
[ 7.350197]
[ 7.355160] Allocated by task 123:
[ 7.355261] kasan_save_stack+0x33/0x60
[ 7.355373] kasan_save_track+0x14/0x30
[ 7.355484] __kasan_kmalloc+0x8f/0xa0
[ 7.355593] ksmbd_conn_alloc+0x44/0x6d0
[ 7.355711] ksmbd_kthread_fn+0x243/0xd70
[ 7.355839] kthread+0x346/0x470
[ 7.355942] ret_from_fork+0x4fb/0x6c0
[ 7.356051] ret_from_fork_asm+0x1a/0x30
[ 7.356164]
[ 7.356214] Freed by task 134:
[ 7.356305] kasan_save_stack+0x33/0x60
[ 7.356416] kasan_save_track+0x14/0x30
[ 7.356527] kasan_save_free_info+0x3b/0x60
[ 7.356646] __kasan_slab_free+0x43/0x70
[ 7.356761] kfree+0x1ca/0x430
[ 7.356862] ksmbd_tcp_disconnect+0x59/0xe0
[ 7.356993] ksmbd_conn_handler_loop+0x77e/0xd40
[ 7.357138] kthread+0x346/0x470
[ 7.357240] ret_from_fork+0x4fb/0x6c0
[ 7.357350] ret_from_fork_asm+0x1a/0x30
[ 7.357463]
[ 7.357513] The buggy address belongs to the object at ffff8881056ac000
[ 7.357513] which belongs to the cache kmalloc-1k of size 1024
[ 7.357857] The buggy address is located 396 bytes inside of
[ 7.357857] freed 1024-byte region
---truncated--- |
| 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. |
| 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:
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:
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 |
| In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim
The root cause of this bug is that when 'bpf_link_put' reduces the
refcount of 'shim_link->link.link' to zero, the resource is considered
released but may still be referenced via 'tr->progs_hlist' in
'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in
'bpf_shim_tramp_link_release' is deferred. During this window, another
process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'.
Based on Martin KaFai Lau's suggestions, I have created a simple patch.
To fix this:
Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'.
Only increment the refcount if it is not already zero.
Testing:
I verified the fix by adding a delay in
'bpf_shim_tramp_link_release' to make the bug easier to trigger:
static void bpf_shim_tramp_link_release(struct bpf_link *link)
{
/* ... */
if (!shim_link->trampoline)
return;
+ msleep(100);
WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link,
shim_link->trampoline, NULL));
bpf_trampoline_put(shim_link->trampoline);
}
Before the patch, running a PoC easily reproduced the crash(almost 100%)
with a call trace similar to KaiyanM's report.
After the patch, the bug no longer occurs even after millions of
iterations. |
| 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. |
