| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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. |
| 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. |
| 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. |
| 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. |
| 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:
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. |
| 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.) |
| 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. |
| 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). |
| 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. |
| 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. |
| Improper access control in Microsoft Office allows an unauthorized attacker to perform spoofing locally. |
| A vulnerability was identified in h2oai h2o-3 up to 7402. Affected by this issue is the function importFiles of the file h2o-core/src/main/java/water/persist/PersistNFS.java of the component ImportFile API. Such manipulation leads to information disclosure. The attack can be executed remotely. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure but did not respond in any way. |
| A weakness has been identified in h2oai h2o-3 up to 7402. This vulnerability affects the function exec of the file h2o-core/src/main/java/water/rapids/ast/prims/misc/AstSetProperty.java of the component Rapids setproperty Primitive Handler. Executing a manipulation can lead to improper access controls. The attack may be performed from remote. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure but did not respond in any way. |
| Insufficient validation of untrusted input in ReadingMode in Google Chrome on Mac prior to 148.0.7778.168 allowed a remote attacker who had compromised the renderer process to bypass site Isolation via a crafted HTML page. (Chromium security severity: High) |
| Improper input validation in Microsoft Edge (Chromium-based) allows an unauthorized attacker to bypass a security feature over a network. |
| In the Linux kernel, the following vulnerability has been resolved:
clockevents: Add missing resets of the next_event_forced flag
The prevention mechanism against timer interrupt starvation missed to reset
the next_event_forced flag in a couple of places:
- When the clock event state changes. That can cause the flag to be
stale over a shutdown/startup sequence
- When a non-forced event is armed, which then prevents rearming before
that event. If that event is far out in the future this will cause
missed timer interrupts.
- In the suspend wakeup handler.
That led to stalls which have been reported by several people.
Add the missing resets, which fixes the problems for the reporters. |
| Attacker can use the IMAP SETACL command to inject the anyone permission to user's dovecot-acl file even if imap_acl_allow_anyone=no. This causes folders to be spammed to all users. The impact is limited to being able to spam folders to other users, no unexpected access is gained. Install to fixed version. No publicly available exploits are known. |
| Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.0, the LDAP authentication endpoint does not validate that the submitted password is non-empty before performing a Simple Bind against the LDAP server. The LdapForm Pydantic model accepts password: str with no minimum length constraint, so an empty string passes validation. The subsequent Connection.bind() call succeeds on vulnerable LDAP servers, and the application issues a full session token for the target user. This vulnerability is fixed in 0.9.0. |
| Fleet is open source device management software. Prior to version 4.81.0, Fleet contained a denial-of-service (DoS) issue in the gRPC Launcher `PublishLogs` endpoint. In affected versions, certain unexpected input values were not handled gracefully, which could cause the Fleet server process to terminate while processing an authenticated request from an enrolled Launcher host. An authenticated attacker with access to any enrolled Launcher node key could cause an immediate and complete denial of service by sending a single gRPC request to the `PublishLogs` endpoint. This vulnerability impacts availability only. There is no exposure of sensitive data, no authentication bypass, no privilege escalation, and no integrity impact. Version 4.81.0 contains a patch. If upgrading immediately is not possible, the following mitigations can reduce exposure. Restrict network access to the Fleet gRPC endpoint where feasible (for example, limiting inbound access to known host IP ranges); deploy Fleet behind infrastructure that terminates or filters gRPC traffic if Launcher log ingestion is not required; and/or monitor for repeated Fleet process crashes or unexpected restarts indicating potential exploitation. |
