Export limit exceeded: 351817 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (351817 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-31613 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.1 High |
| In the Linux kernel, the following vulnerability has been resolved: smb: client: fix OOB reads parsing symlink error response When a CREATE returns STATUS_STOPPED_ON_SYMLINK, smb2_check_message() returns success without any length validation, leaving the symlink parsers as the only defense against an untrusted server. symlink_data() walks SMB 3.1.1 error contexts with the loop test "p < end", but reads p->ErrorId at offset 4 and p->ErrorDataLength at offset 0. When the server-controlled ErrorDataLength advances p to within 1-7 bytes of end, the next iteration will read past it. When the matching context is found, sym->SymLinkErrorTag is read at offset 4 from p->ErrorContextData with no check that the symlink header itself fits. smb2_parse_symlink_response() then bounds-checks the substitute name using SMB2_SYMLINK_STRUCT_SIZE as the offset of PathBuffer from iov_base. That value is computed as sizeof(smb2_err_rsp) + sizeof(smb2_symlink_err_rsp), which is correct only when ErrorContextCount == 0. With at least one error context the symlink data sits 8 bytes deeper, and each skipped non-matching context shifts it further by 8 + ALIGN(ErrorDataLength, 8). The check is too short, allowing the substitute name read to run past iov_len. The out-of-bound heap bytes are UTF-16-decoded into the symlink target and returned to userspace via readlink(2). Fix this all up by making the loops test require the full context header to fit, rejecting sym if its header runs past end, and bound the substitute name against the actual position of sym->PathBuffer rather than a fixed offset. Because sub_offs and sub_len are 16bits, the pointer math will not overflow here with the new greater-than. | ||||
| CVE-2026-31432 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.8 High |
| In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix OOB write in QUERY_INFO for compound requests When a compound request such as READ + QUERY_INFO(Security) is received, and the first command (READ) consumes most of the response buffer, ksmbd could write beyond the allocated buffer while building a security descriptor. The root cause was that smb2_get_info_sec() checked buffer space using ppntsd_size from xattr, while build_sec_desc() often synthesized a significantly larger descriptor from POSIX ACLs. This patch introduces smb_acl_sec_desc_scratch_len() to accurately compute the final descriptor size beforehand, performs proper buffer checking with smb2_calc_max_out_buf_len(), and uses exact-sized allocation + iov pinning. | ||||
| CVE-2026-31426 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7 High |
| 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 | ||||
| CVE-2026-31417 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.5 High |
| In the Linux kernel, the following vulnerability has been resolved: net/x25: Fix overflow when accumulating packets Add a check to ensure that `x25_sock.fraglen` does not overflow. The `fraglen` also needs to be resetted when purging `fragment_queue` in `x25_clear_queues()`. | ||||
| CVE-2026-31413 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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. | ||||
| CVE-2026-31409 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.8 High |
| 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. | ||||
| CVE-2026-31408 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.8 High |
| 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. | ||||
| CVE-2026-31407 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.1 High |
| 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. | ||||
| CVE-2026-31406 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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(). | ||||
| CVE-2026-31393 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.1 High |
| In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access l2cap_information_rsp() checks that cmd_len covers the fixed l2cap_info_rsp header (type + result, 4 bytes) but then reads rsp->data without verifying that the payload is present: - L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads 4 bytes past the header (needs cmd_len >= 8). - L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header (needs cmd_len >= 5). A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an out-of-bounds read of adjacent skb data. Guard each data access with the required payload length check. If the payload is too short, skip the read and let the state machine complete with safe defaults (feat_mask and remote_fixed_chan remain zero from kzalloc), so the info timer cleanup and l2cap_conn_start() still run and the connection is not stalled. | ||||
| CVE-2026-31392 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.1 High |
| 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 ``` | ||||
| CVE-2026-31389 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: spi: fix use-after-free on controller registration failure Make sure to deregister from driver core also in the unlikely event that per-cpu statistics allocation fails during controller registration to avoid use-after-free (of driver resources) and unclocked register accesses. | ||||
| CVE-2026-23466 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: drm/xe: Open-code GGTT MMIO access protection GGTT MMIO access is currently protected by hotplug (drm_dev_enter), which works correctly when the driver loads successfully and is later unbound or unloaded. However, if driver load fails, this protection is insufficient because drm_dev_unplug() is never called. Additionally, devm release functions cannot guarantee that all BOs with GGTT mappings are destroyed before the GGTT MMIO region is removed, as some BOs may be freed asynchronously by worker threads. To address this, introduce an open-coded flag, protected by the GGTT lock, that guards GGTT MMIO access. The flag is cleared during the dev_fini_ggtt devm release function to ensure MMIO access is disabled once teardown begins. (cherry picked from commit 4f3a998a173b4325c2efd90bdadc6ccd3ad9a431) | ||||
| CVE-2026-23462 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.8 High |
| In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HIDP: Fix possible UAF This fixes the following trace caused by not dropping l2cap_conn reference when user->remove callback is called: [ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00 [ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy) [ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 97.809947] Call Trace: [ 97.809954] <TASK> [ 97.809961] dump_stack_lvl (lib/dump_stack.c:122) [ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808) [ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798) [ 97.810055] l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1)) [ 97.810086] ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341) [ 97.810117] hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2)) [ 97.810148] hci_dev_close_sync (net/bluetooth/hci_sync.c:5360) [ 97.810180] ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285) [ 97.810212] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810242] ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5)) [ 97.810267] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810290] ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752) [ 97.810320] hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716) [ 97.810346] vhci_release (drivers/bluetooth/hci_vhci.c:691) [ 97.810375] ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678) [ 97.810404] __fput (fs/file_table.c:470) [ 97.810430] task_work_run (kernel/task_work.c:235) [ 97.810451] ? __pfx_task_work_run (kernel/task_work.c:201) [ 97.810472] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810495] ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5)) [ 97.810527] do_exit (kernel/exit.c:972) [ 97.810547] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810574] ? __pfx_do_exit (kernel/exit.c:897) [ 97.810594] ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6)) [ 97.810616] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810639] ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4)) [ 97.810664] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810688] ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1)) [ 97.810721] do_group_exit (kernel/exit.c:1093) [ 97.810745] get_signal (kernel/signal.c:3007 (discriminator 1)) [ 97.810772] ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366) [ 97.810803] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810826] ? vfs_read (fs/read_write.c:555) [ 97.810854] ? __pfx_get_signal (kernel/signal.c:2800) [ 97.810880] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810905] ? __pfx_vfs_read (fs/read_write.c:555) [ 97.810932] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810960] arch_do_signal_or_restart (arch/ ---truncated--- | ||||
| CVE-2026-23461 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.8 High |
| In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user After commit ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in hci_chan_del"), l2cap_conn_del() uses conn->lock to protect access to conn->users. However, l2cap_register_user() and l2cap_unregister_user() don't use conn->lock, creating a race condition where these functions can access conn->users and conn->hchan concurrently with l2cap_conn_del(). This can lead to use-after-free and list corruption bugs, as reported by syzbot. Fix this by changing l2cap_register_user() and l2cap_unregister_user() to use conn->lock instead of hci_dev_lock(), ensuring consistent locking for the l2cap_conn structure. | ||||
| CVE-2026-23459 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.2 High |
| In the Linux kernel, the following vulnerability has been resolved: ip_tunnel: adapt iptunnel_xmit_stats() to NETDEV_PCPU_STAT_DSTATS Blamed commits forgot that vxlan/geneve use udp_tunnel[6]_xmit_skb() which call iptunnel_xmit_stats(). iptunnel_xmit_stats() was assuming tunnels were only using NETDEV_PCPU_STAT_TSTATS. @syncp offset in pcpu_sw_netstats and pcpu_dstats is different. 32bit kernels would either have corruptions or freezes if the syncp sequence was overwritten. This patch also moves pcpu_stat_type closer to dev->{t,d}stats to avoid a potential cache line miss since iptunnel_xmit_stats() needs to read it. | ||||
| CVE-2026-23458 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the conntrack reference immediately after netlink_dump_start(). When the dump spans multiple rounds, the second recvmsg() triggers the dump callback which dereferences the now-freed conntrack via nfct_help(ct), leading to a use-after-free on ct->ext. The bug is that the netlink_dump_control has no .start or .done callbacks to manage the conntrack reference across dump rounds. Other dump functions in the same file (e.g. ctnetlink_get_conntrack) properly use .start/.done callbacks for this purpose. Fix this by adding .start and .done callbacks that hold and release the conntrack reference for the duration of the dump, and move the nfct_help() call after the cb->args[0] early-return check in the dump callback to avoid dereferencing ct->ext unnecessarily. BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133 CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY Call Trace: <TASK> ctnetlink_exp_ct_dump_table+0x4f/0x2e0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 ? aa_sk_perm+0x184/0x450 sock_recvmsg+0xde/0xf0 Allocated by task 133: kmem_cache_alloc_noprof+0x134/0x440 __nf_conntrack_alloc+0xa8/0x2b0 ctnetlink_create_conntrack+0xa1/0x900 ctnetlink_new_conntrack+0x3cf/0x7d0 nfnetlink_rcv_msg+0x48e/0x510 netlink_rcv_skb+0xc9/0x1f0 nfnetlink_rcv+0xdb/0x220 netlink_unicast+0x3ec/0x590 netlink_sendmsg+0x397/0x690 __sys_sendmsg+0xf4/0x180 Freed by task 0: slab_free_after_rcu_debug+0xad/0x1e0 rcu_core+0x5c3/0x9c0 | ||||
| CVE-2026-23457 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.6 High |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp() sip_help_tcp() parses the SIP Content-Length header with simple_strtoul(), which returns unsigned long, but stores the result in unsigned int clen. On 64-bit systems, values exceeding UINT_MAX are silently truncated before computing the SIP message boundary. For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32, causing the parser to miscalculate where the current message ends. The loop then treats trailing data in the TCP segment as a second SIP message and processes it through the SDP parser. Fix this by changing clen to unsigned long to match the return type of simple_strtoul(), and reject Content-Length values that exceed the remaining TCP payload length. | ||||
| CVE-2026-23456 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.2 High |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case In decode_int(), the CONS case calls get_bits(bs, 2) to read a length value, then calls get_uint(bs, len) without checking that len bytes remain in the buffer. The existing boundary check only validates the 2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint() reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte slab-out-of-bounds read. Add a boundary check for len bytes after get_bits() and before get_uint(). | ||||
| CVE-2026-23455 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 9.1 Critical |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: check for zero length in DecodeQ931() In DecodeQ931(), the UserUserIE code path reads a 16-bit length from the packet, then decrements it by 1 to skip the protocol discriminator byte before passing it to DecodeH323_UserInformation(). If the encoded length is 0, the decrement wraps to -1, which is then passed as a large value to the decoder, leading to an out-of-bounds read. Add a check to ensure len is positive after the decrement. | ||||