Export limit exceeded: 348989 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (348989 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-33516 | 1 Neutrinolabs | 1 Xrdp | 2026-04-27 | 9.1 Critical |
| xrdp is an open source RDP server. Versions through 0.10.5 contain an out-of-bounds read vulnerability during the RDP capability exchange phase. The issue occurs when memory is accessed before validating the remaining buffer length. A remote, unauthenticated attacker can trigger this vulnerability by sending a specially crafted Confirm Active PDU. Successful exploitation could lead to a denial of service (process crash) or potential disclosure of sensitive information from the process memory. This issue has been fixed in version 0.10.6. | ||||
| CVE-2026-6337 | 2026-04-27 | N/A | ||
| ** 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. | ||||
| CVE-2026-35512 | 1 Neutrinolabs | 1 Xrdp | 2026-04-27 | 8.8 High |
| xrdp is an open source RDP server. Versions through 0.10.5 have a heap-based buffer overflow in the EGFX (graphics dynamic virtual channel) implementation due to insufficient validation of client-controlled size parameters, allowing an out-of-bounds write via crafted PDUs. Pre-authentication exploitation can crash the process, while post-authentication exploitation may achieve remote code execution. This issue has been fixed in version 0.10.6. If users are unable to immediately update, they should run xrdp as a non-privileged user (default since 0.10.2) to limit the impact of successful exploitation. | ||||
| CVE-2026-33689 | 1 Neutrinolabs | 1 Xrdp | 2026-04-27 | 9.1 Critical |
| xrdp is an open source RDP server. Versions through 0.10.5 have an out-of-bounds read vulnerability in the pre-authentication RDP message parsing logic. A remote, unauthenticated attacker can trigger this flaw by sending a specially crafted sequence of packets during the initial connection phase. This vulnerability results from insufficient validation of input buffer lengths before processing dynamic channel communication. Successful exploitation can lead to a denial-of-service (DoS) condition via a process crash or potential disclosure of sensitive information from the service's memory space. This issue has been fixed in version 0.10.6. | ||||
| CVE-2026-33145 | 1 Neutrinolabs | 1 Xrdp | 2026-04-27 | 6.3 Medium |
| xrdp is an open source RDP server. Versions through 0.10.5 allow an authenticated remote user to execute arbitrary commands on the server due to unsafe handling of the AlternateShell parameter in xrdp-sesman. When the AllowAlternateShell setting is enabled (which is the default when not explicitly configured), xrdp accepts a client-supplied AlternateShell value and executes it via /bin/sh -c during session initialization. This results in shell-interpreted execution of unsanitized, user-controlled input. This behavior effectively provides a scriptable remote command execution primitive over RDP within the security context of the authenticated user, occurring prior to normal window manager startup. This can bypass expected session initialization flows and operational assumptions that restrict execution to interactive desktop environments. This issue has been fixed in version 0.10.6. | ||||
| CVE-2026-40572 | 1 Minecanton209 | 1 Novumos | 2026-04-27 | 9 Critical |
| NovumOS is a custom 32-bit operating system written in Zig and x86 Assembly. In versions prior to 0.24, Syscall 15 (MemoryMapRange) allows Ring 3 user-mode processes to map arbitrary virtual address ranges into their address space without validating against forbidden regions, including critical kernel structures such as the IDT, GDT, TSS, and page tables. A local attacker can exploit this to modify kernel interrupt handlers, resulting in privilege escalation from user mode to kernel context. This issue has been fixed in version 0.24. | ||||
| CVE-2026-40350 | 1 Leepeuker | 1 Movary | 2026-04-27 | 8.8 High |
| Movary is a self hosted web app to track and rate a user's watched movies. Prior to version 0.71.1, an ordinary authenticated user can access the user-management endpoints `/settings/users` and use them to enumerate all users and create a new administrator account. This happens because the route definitions do not enforce admin-only middleware, and the controller-level authorization check uses a broken boolean condition. As a result, any user with a valid web session cookie can reach functionality that should be restricted to administrators. Version 0.71.1 patches the issue. | ||||
| CVE-2026-40349 | 1 Leepeuker | 1 Movary | 2026-04-27 | 8.8 High |
| Movary is a self hosted web app to track and rate a user's watched movies. Prior to version 0.71.1, an ordinary authenticated user can escalate their own account to administrator by sending `isAdmin=true` to `PUT /settings/users/{userId}` for their own user ID. The endpoint is intended to let a user edit their own profile, but it updates the sensitive `isAdmin` field without any admin-only authorization check. Version 0.71.1 patches the issue. | ||||
| CVE-2026-40317 | 1 Minecanton209 | 1 Novumos | 2026-04-27 | 9.4 Critical |
| NovumOS is a custom 32-bit operating system written in Zig and x86 Assembly. In versions prior to 0.24, Syscall 12 (JumpToUser) accepts an arbitrary entry point address from user-space registers without validation, allowing any Ring 3 user-mode process to jump to kernel addresses and execute arbitrary code in Ring 0 context, resulting in local privilege escalation. This issue has been fixed in version 0.24. If developers are unable to immediately update, they should restrict syscall access by running the system in single-user mode without Ring 3, and disable user-mode processes by only running kernel shell with no user processes. This issue has been fixed in version 0.24. | ||||
| 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-2026-31436 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 9.8 Critical |
| In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: fix possible wrong descriptor completion in llist_abort_desc() At the end of this function, d is the traversal cursor of flist, but the code completes found instead. This can lead to issues such as NULL pointer dereferences, double completion, or descriptor leaks. Fix this by completing d instead of found in the final list_for_each_entry_safe() loop. | ||||
| 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-2026-31405 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 9.8 Critical |
| 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. | ||||