| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| Insufficient validation of untrusted input in WebML in Google Chrome prior to 147.0.7727.55 allowed a remote attacker to perform an out of bounds memory write via a crafted HTML page. (Chromium security severity: Low) |
| Inappropriate implementation in Navigation in Google Chrome prior to 147.0.7727.55 allowed a remote attacker who had compromised the renderer process to leak cross-origin data via a crafted HTML page. (Chromium security severity: Low) |
| Insufficient validation of untrusted input in WebSockets in Google Chrome prior to 147.0.7727.55 allowed a remote attacker who had compromised the renderer process to bypass same origin policy via a crafted HTML page. (Chromium security severity: Low) |
| Out-of-bounds read in .NET allows an unauthorized attacker to deny service over a network. |
| Incorrect default permissions in .NET allows an authorized attacker to elevate privileges locally. |
| In the Linux kernel, the following vulnerability has been resolved:
net: bonding: fix use-after-free in bond_xmit_broadcast()
bond_xmit_broadcast() reuses the original skb for the last slave
(determined by bond_is_last_slave()) and clones it for others.
Concurrent slave enslave/release can mutate the slave list during
RCU-protected iteration, changing which slave is "last" mid-loop.
This causes the original skb to be double-consumed (double-freed).
Replace the racy bond_is_last_slave() check with a simple index
comparison (i + 1 == slaves_count) against the pre-snapshot slave
count taken via READ_ONCE() before the loop. This preserves the
zero-copy optimization for the last slave while making the "last"
determination stable against concurrent list mutations.
The UAF can trigger the following crash:
==================================================================
BUG: KASAN: slab-use-after-free in skb_clone
Read of size 8 at addr ffff888100ef8d40 by task exploit/147
CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY
Call Trace:
<TASK>
dump_stack_lvl (lib/dump_stack.c:123)
print_report (mm/kasan/report.c:379 mm/kasan/report.c:482)
kasan_report (mm/kasan/report.c:597)
skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108)
bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334)
bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593)
dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887)
__dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838)
ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136)
ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219)
ip6_output (net/ipv6/ip6_output.c:250)
ip6_send_skb (net/ipv6/ip6_output.c:1985)
udp_v6_send_skb (net/ipv6/udp.c:1442)
udpv6_sendmsg (net/ipv6/udp.c:1733)
__sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206)
__x64_sys_sendto (net/socket.c:2209)
do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
</TASK>
Allocated by task 147:
Freed by task 147:
The buggy address belongs to the object at ffff888100ef8c80
which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 192 bytes inside of
freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60)
Memory state around the buggy address:
ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
^
ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb
ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
================================================================== |
| In the Linux kernel, the following vulnerability has been resolved:
bridge: mrp: reject zero test interval to avoid OOM panic
br_mrp_start_test() and br_mrp_start_in_test() accept the user-supplied
interval value from netlink without validation. When interval is 0,
usecs_to_jiffies(0) yields 0, causing the delayed work
(br_mrp_test_work_expired / br_mrp_in_test_work_expired) to reschedule
itself with zero delay. This creates a tight loop on system_percpu_wq
that allocates and transmits MRP test frames at maximum rate, exhausting
all system memory and causing a kernel panic via OOM deadlock.
The same zero-interval issue applies to br_mrp_start_in_test_parse()
for interconnect test frames.
Use NLA_POLICY_MIN(NLA_U32, 1) in the nla_policy tables for both
IFLA_BRIDGE_MRP_START_TEST_INTERVAL and
IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL, so zero is rejected at the
netlink attribute parsing layer before the value ever reaches the
workqueue scheduling code. This is consistent with how other bridge
subsystems (br_fdb, br_mst) enforce range constraints on netlink
attributes. |
| 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 |
| There exists an arbitrary memory read within the Linux Kernel BPF - Constants provided to fill pointers in structs passed in to bpf_sys_bpf are not verified and can point anywhere, including memory not owned by BPF. An attacker with CAP_BPF can arbitrarily read memory from anywhere on the system. We recommend upgrading past commit 86f44fcec22c |
| An issue was discovered in the Linux kernel 5.8.9. The WEP, WPA, WPA2, and WPA3 implementations reassemble fragments even though some of them were sent in plaintext. This vulnerability can be abused to inject packets and/or exfiltrate selected fragments when another device sends fragmented frames and the WEP, CCMP, or GCMP data-confidentiality protocol is used. |
| The 802.11 standard that underpins Wi-Fi Protected Access (WPA, WPA2, and WPA3) and Wired Equivalent Privacy (WEP) doesn't require that the A-MSDU flag in the plaintext QoS header field is authenticated. Against devices that support receiving non-SSP A-MSDU frames (which is mandatory as part of 802.11n), an adversary can abuse this to inject arbitrary network packets. |
| In the Linux kernel, the following vulnerability has been resolved:
usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks()
The `check_command_size_in_blocks()` function calculates the data size
in bytes by left shifting `common->data_size_from_cmnd` by the block
size (`common->curlun->blkbits`). However, it does not validate whether
this shift operation will cause an integer overflow.
Initially, the block size is set up in `fsg_lun_open()` , and the
`common->data_size_from_cmnd` is set up in `do_scsi_command()`. During
initialization, there is no integer overflow check for the interaction
between two variables.
So if a malicious USB host sends a SCSI READ or WRITE command
requesting a large amount of data (`common->data_size_from_cmnd`), the
left shift operation can wrap around. This results in a truncated data
size, which can bypass boundary checks and potentially lead to memory
corruption or out-of-bounds accesses.
Fix this by using the check_shl_overflow() macro to safely perform the
shift and catch any overflows. |
| In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix unsound scalar forking in maybe_fork_scalars() for BPF_OR
maybe_fork_scalars() is called for both BPF_AND and BPF_OR when the
source operand is a constant. When dst has signed range [-1, 0], it
forks the verifier state: the pushed path gets dst = 0, the current
path gets dst = -1.
For BPF_AND this is correct: 0 & K == 0.
For BPF_OR this is wrong: 0 | K == K, not 0.
The pushed path therefore tracks dst as 0 when the runtime value is K,
producing an exploitable verifier/runtime divergence that allows
out-of-bounds map access.
Fix this by passing env->insn_idx (instead of env->insn_idx + 1) to
push_stack(), so the pushed path re-executes the ALU instruction with
dst = 0 and naturally computes the correct result for any opcode. |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
| In the Linux kernel, the following vulnerability has been resolved:
net: atm: fix crash due to unvalidated vcc pointer in sigd_send()
Reproducer available at [1].
The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc
pointer from msg->vcc and uses it directly without any validation. This
pointer comes from userspace via sendmsg() and can be arbitrarily forged:
int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0);
ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon
struct msghdr msg = { .msg_iov = &iov, ... };
*(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer
sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef
In normal operation, the kernel sends the vcc pointer to the signaling
daemon via sigd_enq() when processing operations like connect(), bind(),
or listen(). The daemon is expected to return the same pointer when
responding. However, a malicious daemon can send arbitrary pointer values.
Fix this by introducing find_get_vcc() which validates the pointer by
searching through vcc_hash (similar to how sigd_close() iterates over
all VCCs), and acquires a reference via sock_hold() if found.
Since struct atm_vcc embeds struct sock as its first member, they share
the same lifetime. Therefore using sock_hold/sock_put is sufficient to
keep the vcc alive while it is being used.
Note that there may be a race with sigd_close() which could mark the vcc
with various flags (e.g., ATM_VF_RELEASED) after find_get_vcc() returns.
However, sock_hold() guarantees the memory remains valid, so this race
only affects the logical state, not memory safety.
[1]: https://gist.github.com/mrpre/1ba5949c45529c511152e2f4c755b0f3 |
| 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(). |
| 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. |
| In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold
sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately
releases the lock without holding a reference to the socket. A concurrent
close() can free the socket between the lock release and the subsequent
sk->sk_state access, resulting in a use-after-free.
Other functions in the same file (sco_sock_timeout(), sco_conn_del())
correctly use sco_sock_hold() to safely hold a reference under the lock.
Fix by using sco_sock_hold() to take a reference before releasing the
lock, and adding sock_put() on all exit paths. |
| 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(). |
