| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: conntrack: add missing netlink policy validations
Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink.
These attributes are used by the kernel without any validation.
Extend the netlink policies accordingly.
Quoting the reporter:
nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE
value directly to ct->proto.sctp.state without checking that it is
within the valid range. [..]
and: ... with exp->dir = 100, the access at
ct->master->tuplehash[100] reads 5600 bytes past the start of a
320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by
UBSAN. |
| 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:
media: dvb-net: fix OOB access in ULE extension header tables
The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables
in handle_one_ule_extension() are declared with 255 elements (valid
indices 0-254), but the index htype is derived from network-controlled
data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When
htype equals 255, an out-of-bounds read occurs on the function pointer
table, and the OOB value may be called as a function pointer.
Add a bounds check on htype against the array size before either table
is accessed. Out-of-range values now cause the SNDU to be discarded. |
| In the Linux kernel, the following vulnerability has been resolved:
fs/xattr: missing fdput() in fremovexattr error path
In the Linux kernel, the fremovexattr() syscall calls fdget() to acquire a
file reference but returns early without calling fdput() when
strncpy_from_user() fails on the name argument. In multi-threaded processes
where fdget() takes the slow path, this permanently leaks one
file reference per call, pinning the struct file and associated kernel
objects in memory. An unprivileged local user can exploit this to cause
kernel memory exhaustion. The issue was inadvertently fixed by commit
a71874379ec8 ("xattr: switch to CLASS(fd)"). |
| A flaw was found in Corosync. An integer overflow vulnerability in Corosync's join message sanity validation allows a remote, unauthenticated attacker to send crafted User Datagram Protocol (UDP) packets. This can cause the service to crash, leading to a denial of service. This vulnerability specifically affects Corosync deployments configured to use totemudp/totemudpu mode. |
| A flaw was found in Corosync. A remote unauthenticated attacker can exploit a wrong return value vulnerability in the Corosync membership commit token sanity check by sending a specially crafted User Datagram Protocol (UDP) packet. This can lead to an out-of-bounds read, causing a denial of service (DoS) and potentially disclosing limited memory contents. This vulnerability affects Corosync when running in totemudp/totemudpu mode, which is the default configuration. |
| A vulnerability was found in assafelovic gpt-researcher up to 3.4.3. This impacts an unknown function of the component HTTP REST API Endpoint. Performing a manipulation results in missing authentication. It is possible to initiate the attack remotely. The exploit has been made public and could be used. The project was informed of the problem early through an issue report but has not responded yet. |
| A vulnerability has been found in assafelovic gpt-researcher up to 3.4.3. This affects the function extract_command_data of the file backend/server/server_utils.py of the component ws Endpoint. Such manipulation of the argument args leads to code injection. The attack may be performed from remote. The exploit has been disclosed to the public and may be used. The project was informed of the problem early through an issue report but has not responded yet. |
| A flaw has been found in assafelovic gpt-researcher up to 3.4.3. The impacted element is an unknown function of the file backend/server/app.py of the component Report API. This manipulation causes cross site scripting. The attack is possible to be carried out remotely. The exploit has been published and may be used. The project was informed of the problem early through an issue report but has not responded yet. |
| In the Linux kernel, the following vulnerability has been resolved:
mac80211: fix crash in ieee80211_chan_bw_change for AP_VLAN stations
ieee80211_chan_bw_change() iterates all stations and accesses
link->reserved.oper via sta->sdata->link[link_id]. For stations on
AP_VLAN interfaces (e.g. 4addr WDS clients), sta->sdata points to
the VLAN sdata, whose link never participates in chanctx reservations.
This leaves link->reserved.oper zero-initialized with chan == NULL,
causing a NULL pointer dereference in __ieee80211_sta_cap_rx_bw()
when accessing chandef->chan->band during CSA.
Resolve the VLAN sdata to its parent AP sdata using get_bss_sdata()
before accessing link data.
[also change sta->sdata in ARRAY_SIZE even if it doesn't matter] |
| In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix krb5 mount with username option
Customer reported that some of their krb5 mounts were failing against
a single server as the client was trying to mount the shares with
wrong credentials. It turned out the client was reusing SMB session
from first mount to try mounting the other shares, even though a
different username= option had been specified to the other mounts.
By using username mount option along with sec=krb5 to search for
principals from keytab is supported by cifs.upcall(8) since
cifs-utils-4.8. So fix this by matching username mount option in
match_session() even with Kerberos.
For example, the second mount below should fail with -ENOKEY as there
is no 'foobar' principal in keytab (/etc/krb5.keytab). The client
ends up reusing SMB session from first mount to perform the second
one, which is wrong.
```
$ ktutil
ktutil: add_entry -password -p testuser -k 1 -e aes256-cts
Password for testuser@ZELDA.TEST:
ktutil: write_kt /etc/krb5.keytab
ktutil: quit
$ klist -ke
Keytab name: FILE:/etc/krb5.keytab
KVNO Principal
---- ----------------------------------------------------------------
1 testuser@ZELDA.TEST (aes256-cts-hmac-sha1-96)
$ mount.cifs //w22-root2/scratch /mnt/1 -o sec=krb5,username=testuser
$ mount.cifs //w22-root2/scratch /mnt/2 -o sec=krb5,username=foobar
$ mount -t cifs | grep -Po 'username=\K\w+'
testuser
testuser
``` |
| In the Linux kernel, the following vulnerability has been resolved:
serial: core: fix infinite loop in handle_tx() for PORT_UNKNOWN
uart_write_room() and uart_write() behave inconsistently when
xmit_buf is NULL (which happens for PORT_UNKNOWN ports that were
never properly initialized):
- uart_write_room() returns kfifo_avail() which can be > 0
- uart_write() checks xmit_buf and returns 0 if NULL
This inconsistency causes an infinite loop in drivers that rely on
tty_write_room() to determine if they can write:
while (tty_write_room(tty) > 0) {
written = tty->ops->write(...);
// written is always 0, loop never exits
}
For example, caif_serial's handle_tx() enters an infinite loop when
used with PORT_UNKNOWN serial ports, causing system hangs.
Fix by making uart_write_room() also check xmit_buf and return 0 if
it's NULL, consistent with uart_write().
Reproducer: https://gist.github.com/mrpre/d9a694cc0e19828ee3bc3b37983fde13 |
| In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: Limit BO list entry count to prevent resource exhaustion
Userspace can pass an arbitrary number of BO list entries via the
bo_number field. Although the previous multiplication overflow check
prevents out-of-bounds allocation, a large number of entries could still
cause excessive memory allocation (up to potentially gigabytes) and
unnecessarily long list processing times.
Introduce a hard limit of 128k entries per BO list, which is more than
sufficient for any realistic use case (e.g., a single list containing all
buffers in a large scene). This prevents memory exhaustion attacks and
ensures predictable performance.
Return -EINVAL if the requested entry count exceeds the limit
(cherry picked from commit 688b87d39e0aa8135105b40dc167d74b5ada5332) |
| A vulnerability was detected in Belkin F9K1015 1.00.10. The affected element is the function formSetFirewall of the file /goform/formSetFirewall. The manipulation of the argument webpage results in stack-based buffer overflow. The attack can be executed remotely. The exploit is now public and may be used. The vendor was contacted early about this disclosure but did not respond in any way. |
| A weakness has been identified in assafelovic gpt-researcher up to 3.4.3. This issue affects some unknown processing of the file gpt_researcher/skills/researcher.py of the component WebSocket Interface. Executing a manipulation of the argument task can lead to cross site scripting. The attack may be launched remotely. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet. |
| A security flaw has been discovered in ProjectSend r2002. This vulnerability affects unknown code of the file upload.php. Performing a manipulation results in cross-site request forgery. The attack may be initiated remotely. The exploit has been released to the public and may be used for attacks. Upgrading to version r2029 is able to resolve this issue. The patch is named 2c0d25824ab571b6c219ac1a188ad9350149661b. You should upgrade the affected component. |
| A vulnerability was identified in hcengineering Huly Platform 0.7.382. This affects an unknown part of the file server/front/src/index.ts of the component Import Endpoint. Such manipulation leads to server-side request forgery. The attack can be launched 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 vulnerability was determined in hcengineering Huly Platform 0.7.382. Affected by this issue is some unknown functionality of the file foundations/core/packages/token/src/token.ts of the component JWT Token Handler. This manipulation of the argument SERVER_SECRET with the input secret causes use of hard-coded cryptographic key
. The attack can be initiated remotely. The attack is considered to have high complexity. The exploitation is known to be difficult. The vendor was contacted early about this disclosure but did not respond in any way. |
| A vulnerability was found in ChrisChinchilla Vale-MCP up to 0.1.0. Affected by this vulnerability is an unknown functionality of the file src/index.ts of the component HTTP Interface. The manipulation of the argument config_path results in os command injection. Attacking locally is a requirement. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way. |
| A vulnerability has been found in itsourcecode Construction Management System 1.0. Affected is an unknown function of the file /borrowed_equip_report.php of the component Parameter Handler. The manipulation of the argument Home leads to sql injection. It is possible to initiate the attack remotely. The exploit has been disclosed to the public and may be used. |
