| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| Frappe is a full-stack web application framework. Prior to 16.14.0 and 15.104.0, Frappe has a SQL injection in bulk_update. This vulnerability is fixed in 16.14.0 and 15.104.0. |
| Sereal::Encoder versions from 4.000 through 4.009_002 for Perl embeds a vulnerable version of the Zstandard library.
Sereal::Encoder embeds a version of the Zstandard (zstd) library that is vulnerable to CVE-2019-11922. This is a race condition in the one-pass compression functions of Zstandard prior to version 1.3.8 could allow an attacker to write bytes out of bounds if an output buffer smaller than the recommended size was used. |
| Transient DOS when receiving a service data frame with excessive length during device matching over a neighborhood awareness network protocol connection. |
| ASDA-Soft Stack-based Buffer Overflow Vulnerability |
| An attacker might be able to inject HTML content into the internal web dashboard by sending crafted DNS queries to a DNSdist instance where domain-based dynamic rules have been enabled via either DynBlockRulesGroup:setSuffixMatchRule or DynBlockRulesGroup:setSuffixMatchRuleFFI. |
| A flaw was found in libssh. A remote attacker, by controlling client configuration files or known_hosts files, could craft specific hostnames that when processed by the `match_pattern()` function can lead to inefficient regular expression backtracking. This can cause timeouts and resource exhaustion, resulting in a Denial of Service (DoS) for the client. |
| A flaw was found in libssh in which a malicious SFTP (SSH File Transfer Protocol) server can exploit this by sending a malformed 'longname' field within an `SSH_FXP_NAME` message during a file listing operation. This missing null check can lead to reading beyond allocated memory on the heap. This can cause unexpected behavior or lead to a denial of service (DoS) due to application crashes. |
| Missing Authorization vulnerability in Re Gallery allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects Re Gallery: from n/a through 1.18.9. |
| If a BIND resolver is performing DNSSEC validation and encounters a maliciously crafted zone, the resolver may consume excessive CPU. Authoritative-only servers are generally unaffected, although there are circumstances where authoritative servers may make recursive queries (see: https://kb.isc.org/docs/why-does-my-authoritative-server-make-recursive-queries).
This issue affects BIND 9 versions 9.11.0 through 9.16.50, 9.18.0 through 9.18.46, 9.20.0 through 9.20.20, 9.21.0 through 9.21.19, 9.11.3-S1 through 9.16.50-S1, 9.18.11-S1 through 9.18.46-S1, and 9.20.9-S1 through 9.20.20-S1. |
| A vulnerability was identified in Unidocs ezPDF DRM Reader and ezPDF Reader 2.0/3.0.0.4. This affects an unknown part in the library SHFOLDER.dll. Such manipulation leads to uncontrolled search path. The attack needs to be performed locally. Attacks of this nature are highly complex. It is indicated that the exploitability is difficult. The exploit is publicly available and might be used. Upgrading the affected component is recommended. The vendor explains: "[W]e have already addressed similar DLL search path vulnerability patterns through prior security updates. (...) Users are advised to use the latest version provided by the vendor." |
| In the Linux kernel, the following vulnerability has been resolved:
xen/privcmd: restrict usage in unprivileged domU
The Xen privcmd driver allows to issue arbitrary hypercalls from
user space processes. This is normally no problem, as access is
usually limited to root and the hypervisor will deny any hypercalls
affecting other domains.
In case the guest is booted using secure boot, however, the privcmd
driver would be enabling a root user process to modify e.g. kernel
memory contents, thus breaking the secure boot feature.
The only known case where an unprivileged domU is really needing to
use the privcmd driver is the case when it is acting as the device
model for another guest. In this case all hypercalls issued via the
privcmd driver will target that other guest.
Fortunately the privcmd driver can already be locked down to allow
only hypercalls targeting a specific domain, but this mode can be
activated from user land only today.
The target domain can be obtained from Xenstore, so when not running
in dom0 restrict the privcmd driver to that target domain from the
beginning, resolving the potential problem of breaking secure boot.
This is XSA-482
---
V2:
- defer reading from Xenstore if Xenstore isn't ready yet (Jan Beulich)
- wait in open() if target domain isn't known yet
- issue message in case no target domain found (Jan Beulich) |
| 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:
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:
NFSD: Defer sub-object cleanup in export put callbacks
svc_export_put() calls path_put() and auth_domain_put() immediately
when the last reference drops, before the RCU grace period. RCU
readers in e_show() and c_show() access both ex_path (via
seq_path/d_path) and ex_client->name (via seq_escape) without
holding a reference. If cache_clean removes the entry and drops the
last reference concurrently, the sub-objects are freed while still
in use, producing a NULL pointer dereference in d_path.
Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or
ex_stats") moved kfree of ex_uuid and ex_stats into the
call_rcu callback, but left path_put() and auth_domain_put() running
before the grace period because both may sleep and call_rcu
callbacks execute in softirq context.
Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the
callback until after the RCU grace period and executes it in process
context where sleeping is permitted. This allows path_put() and
auth_domain_put() to be moved into the deferred callback alongside
the other resource releases. Apply the same fix to expkey_put(),
which has the identical pattern with ek_path and ek_client.
A dedicated workqueue scopes the shutdown drain to only NFSD
export release work items; flushing the shared
system_unbound_wq would stall on unrelated work from other
subsystems. nfsd_export_shutdown() uses rcu_barrier() followed
by flush_workqueue() to ensure all deferred release callbacks
complete before the export caches are destroyed.
Reviwed-by: Jeff Layton <jlayton@kernel.org> |
| In the Linux kernel, the following vulnerability has been resolved:
NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd
The /proc/fs/nfs/exports proc entry is created at module init
and persists for the module's lifetime. exports_proc_open()
captures the caller's current network namespace and stores
its svc_export_cache in seq->private, but takes no reference
on the namespace. If the namespace is subsequently torn down
(e.g. container destruction after the opener does setns() to a
different namespace), nfsd_net_exit() calls nfsd_export_shutdown()
which frees the cache. Subsequent reads on the still-open fd
dereference the freed cache_detail, walking a freed hash table.
Hold a reference on the struct net for the lifetime of the open
file descriptor. This prevents nfsd_net_exit() from running --
and thus prevents nfsd_export_shutdown() from freeing the cache
-- while any exports fd is open. cache_detail already stores
its net pointer (cd->net, set by cache_create_net()), so
exports_release() can retrieve it without additional per-file
storage. |
