| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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(). |
| ** REJECT ** DO NOT USE THIS CANDIDATE NUMBER. Reason: This candidate was issued in error. Notes: All references and descriptions in this candidate have been removed to prevent accidental usage. |
| 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:
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. |
| Improper Neutralization of Input During Web Page Generation ("Cross-site Scripting") vulnerability in Drupal Colorbox Inline allows Cross-Site Scripting (XSS).
This issue affects Colorbox Inline: from 0.0.0 before 2.1.1. |
| 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:
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(). |
| A Use-After-Free vulnerability has been discovered in GRUB's gettext module. This flaw stems from a programming error where the gettext command remains registered in memory after its module is unloaded. An attacker can exploit this condition by invoking the orphaned command, causing the application to access a memory location that is no longer valid. An attacker could exploit this vulnerability to cause grub to crash, leading to a Denial of Service. Possible data integrity or confidentiality compromise is not discarded. |
| A flaw was found in Keycloak. A broken access control vulnerability in the Account Resources user lookup endpoint allows a remote authenticated user, who owns at least one User-Managed Access (UMA) resource, to enumerate and harvest personally identifiable information (PII) for all realm users. By sending crafted requests with arbitrary usernames or email values, the endpoint returns full profile objects for unrelated users. This leads to broad profile-level information disclosure. |
| A flaw was found in Keycloak. This authentication vulnerability allows a remote attacker to replay `ExecuteActionsActionToken` tokens within Keycloak's WebAuthn (Web Authentication) flow. By intercepting an execute-actions email link, an attacker can register their own authenticator to a victim's account. This leads to unauthorized enrollment of a hardware-backed credential, enabling persistent account takeover. |
| A flaw was found in Keycloak. A low-privilege administrator with the 'view-clients' role can exploit this by invoking the 'evaluate-scopes' Admin API endpoints with an arbitrary user ID (userId) parameter. This vulnerability allows for cross-role personally identifiable information (PII) leakage, enabling unauthorized visibility into user identities and authorizations across the realm. Exploitation is possible remotely via network access to the Admin API. |
| A flaw was found in Keycloak. This access control vulnerability in Keycloak's OpenID Connect (OIDC) token introspection endpoint allows a confidential client to bypass audience restrictions. An attacker-controlled client with valid credentials can retrieve sensitive token claims intended for other resource servers, compromising the confidentiality of lightweight access tokens. This issue can be exploited remotely by any confidential client in the realm with valid credentials. |
| A flaw was found in Keycloak. A low-privilege user, with knowledge of user credentials and client ID, can bypass a security control intended to disable the implicit flow in OpenID Connect (OIDC) clients. By manipulating client data during a session restart, an attacker can obtain an access token that should not be available. This vulnerability can also lead to the exposure of these access tokens in server logs, proxy logs, and HTTP Referrer headers, resulting in sensitive information disclosure. |
| A flaw was found in Keycloak. An authenticated client could exploit an Insecure Direct Object Reference (IDOR) vulnerability in the Authorization Services Protection API endpoint. By knowing or obtaining a resource's unique identifier (UUID) belonging to another Resource Server within the same realm, the client could bypass authorization checks. This allows the client to perform unauthorized GET, PUT, and DELETE operations on resources, leading to information disclosure and potential unauthorized modification or deletion of data. |
| In the Linux kernel, the following vulnerability has been resolved:
crypto: pcrypt - Fix handling of MAY_BACKLOG requests
MAY_BACKLOG requests can return EBUSY. Handle them by checking
for that value and filtering out EINPROGRESS notifications. |
| 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. |
| In the Linux kernel, the following vulnerability has been resolved:
hwmon: (pmbus/q54sj108a2) fix stack overflow in debugfs read
The q54sj108a2_debugfs_read function suffers from a stack buffer overflow
due to incorrect arguments passed to bin2hex(). The function currently
passes 'data' as the destination and 'data_char' as the source.
Because bin2hex() converts each input byte into two hex characters, a
32-byte block read results in 64 bytes of output. Since 'data' is only
34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end
of the buffer onto the stack.
Additionally, the arguments were swapped: it was reading from the
zero-initialized 'data_char' and writing to 'data', resulting in
all-zero output regardless of the actual I2C read.
Fix this by:
1. Expanding 'data_char' to 66 bytes to safely hold the hex output.
2. Correcting the bin2hex() argument order and using the actual read count.
3. Using a pointer to select the correct output buffer for the final
simple_read_from_buffer call. |
| In the Linux kernel, the following vulnerability has been resolved:
smb: server: fix use-after-free in smb2_open()
The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is
dereferenced after rcu_read_unlock(), creating a use-after-free
window. |
| 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 |
| Adobe Commerce versions 2.4.9-beta1, 2.4.8-p4, 2.4.7-p9, 2.4.6-p14, 2.4.5-p16, 2.4.4-p17 and earlier are affected by an Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') vulnerability that could result in arbitrary file system read and write. An authenticated attacker with administrative privileges could exploit this vulnerability to read or write files outside the restricted directory. Exploitation of this issue does not require user interaction. Scope is changed. |
