Vulnerabilities exploitable today
354,756in current view
Single score combining CVSS, KEV membership and EPSS. Every CVE with its own record — timeline from publication to active exploitation.
In KEV catalog1,656
New KEV · 24H0
Exploit Today ≥ 701,601
Distribution · last window
- Critical2,586
- High9,230
- Medium7,495
- Low701
Window
Severity
Flags
CVECVSSEPSSKEVRExploitTitleMod.
CVE-2020-0018—5.6%
——2——CVE-2026-45879—5.6%
——2——CVE-2025-9447—5.6%
——2——CVE-2026-639207.1 HIG5.6%
——2In the Linux kernel, the following vulnerability has been resolved:
ipv6: validate extension header length before copying to cmsg
ip6_datagram_recv_specific_ctl() builds IPV6_{HOPOPTS,DSTOPTS,RTHDR}
cmsgs (and their IPV6_2292* legacy counterparts) by trusting the
on-wire hdrlen byte (ptr[1]) when computing the put_cmsg() length.
The length was validated only at parse time (ipv6_parse_hopopts(),
etc.). An nftables payload-write expression can rewrite hdrlen after
parsing and before the skb reaches recvmsg; the write itself is
in-bounds but put_cmsg() then reads up to ((hdrlen+1) << 3) = 2040
bytes from an 8-byte header. nftables is reachable from an
unprivileged user namespace, so this is an unprivileged
slab-out-of-bounds read:
BUG: KASAN: slab-out-of-bounds in put_cmsg+0x3ac/0x540
put_cmsg+0x3ac/0x540
udpv6_recvmsg+0xca0/0x1250
sock_recvmsg+0xdf/0x190
____sys_recvmsg+0x1b1/0x620
Add ipv6_get_exthdr_len() which validates that at least two bytes
are accessible before reading the hdrlen field, then checks the
computed length against skb_tail_pointer(skb), returning 0 on
failure. Extension headers are kept in the linear skb area by
pskb_may_pull() during input, so skb_tail_pointer() is the correct
bound.
Use ipv6_get_exthdr_len() at all non-AH call sites: the five
standalone cmsg blocks (HbH, 2292HbH, 2292DSTOPTS x2, 2292RTHDR)
and the three standard cases in the extension-header walk loop
(DSTOPTS, ROUTING, default). AH retains an inline bounds check
because its length formula differs ((ptr[1]+2)<<2).
The walk loop also gets a pre-read bounds check at the top to
validate ptr before any case accesses ptr[0] or ptr[1].
When the walk loop detects a corrupted header, return from the
function instead of continuing to process later socket options.5dCVE-2026-639457.8 HIG5.6%
——2In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: ISO: serialize iso_sock_clear_timer with socket lock
iso_sock_close() calls iso_sock_clear_timer() before acquiring
lock_sock(sk).
iso_sock_clear_timer() reads iso_pi(sk)->conn twice without the
socket lock held:
if (!iso_pi(sk)->conn)
return;
cancel_delayed_work(&iso_pi(sk)->conn->timeout_work);
Concurrently, iso_conn_del() executes under lock_sock(sk) and calls
iso_chan_del(), which sets iso_pi(sk)->conn to NULL and may result in
the final reference to the connection being dropped:
CPU0 CPU1
---- ----
iso_sock_clear_timer()
if (conn != NULL) ... lock_sock(sk)
iso_chan_del()
iso_pi(sk)->conn = NULL
cancel_delayed_work(conn) /* NULL deref or UAF */
iso_pi(sk)->conn is not stable across the unlock window, causing a
NULL pointer dereference or use-after-free.
Serialize iso_sock_clear_timer() with the socket lock by moving it
inside lock_sock()/release_sock(), matching the pattern used in
iso_conn_del() and all other call sites.5dCVE-2026-45902—5.6%
——2——CVE-2026-28194—5.6%
——2——CVE-2025-49032—5.6%
——2——CVE-2025-49861—5.6%
——2——CVE-2021-35091—5.6%
——2——CVE-2026-45925—5.6%
——2——CVE-2026-45858—5.6%
——2——CVE-2021-25430—5.6%
——2——CVE-2026-132396.5 MED5.6%
——2Missing Authorization vulnerability in Drupal WissKI allows Forceful Browsing. This issue affects WissKI versions: from 0.0.0 to 4.2.0.19dCVE-2026-33793—5.6%
——2——CVE-2026-132416.5 MED5.6%
——2Missing Authorization vulnerability in Drupal Paragraphs allows Forceful Browsing. This issue affects Paragraphs versions: from 0.0.0 to 1.21.0.11dCVE-2025-71107—5.6%
——2——CVE-2024-54683—5.6%
——2——CVE-2023-30707—5.6%
——2——CVE-2026-314067.8 HIG5.6%
——2In 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().8dCVE-2025-8383—5.6%
——2——CVE-2025-4951—5.5%
——2——CVE-2026-443425.3 MED5.6%
——2New API is a large language mode (LLM) gateway and artificial intelligence (AI) asset management system. Prior to 0.12.0-alpha.1, the email and WeChat account binding endpoints GET /api/oauth/email/bind and GET /api/oauth/wechat/bind used GET requests for state-changing account operations, allowing an attacker to trigger a logged-in user's browser to bind an attacker-controlled email address or OAuth identity in deployments where session cookies could be sent on cross-site navigations. This issue is fixed in version 0.12.0-alpha.1.16dCVE-2026-112984.3 MED5.6%
——2Inappropriate implementation in Chrome for iOS in Google Chrome on iOS prior to 149.0.7827.53 allowed a remote attacker to bypass same origin policy via a crafted HTML page. (Chromium security severity: Low)9dCVE-2026-106606.4 MED5.6%
——2The Bluetooth BAP Broadcast Assistant GATT client in subsys/bluetooth/audio/bap_broadcast_assistant.c reassembled remote Broadcast Receive State data into a single file-static net_buf_simple (att_buf, BT_ATT_MAX_ATTRIBUTE_LEN = 512 bytes) shared by all connection instances, while the BUSY flag, long-read handle, and reset/offset state were per-connection.
When the device acts as a Broadcast Assistant connected to multiple Scan Delegator peripherals, notification and long-read callbacks from different connections interleave on the shared buffer: the append in notify_handler (net_buf_simple_add_mem at the not-busy branch) performs no tailroom check, so receive-state notifications from two or more delegators accumulate on the same 512-byte buffer and, with a sufficiently large configured ATT MTU (BT_L2CAP_TX_MTU up to 2000) and two-to-three concurrent connections, write past the buffer into adjacent .bss (net_buf_simple_add only asserts in debug builds).
Even below the overflow threshold, one connection's net_buf_simple_reset zeroes the shared length while another connection's reassembly and GATT read offset are in flight, mixing one peer's data into another's parse. A malicious or compromised Scan Delegator (or two colluding peers) over BLE can trigger this, causing out-of-bounds writes (memory corruption / denial of service) and cross-connection data corruption.
The fix moves the buffer into the per-connection instance struct so each connection reassembles into its own buffer. Affects Zephyr releases shipping the Broadcast Assistant with the shared buffer, including v4.4.0 and earlier.18dCVE-2021-1932—5.6%
——2——CVE-2025-36410—5.6%
——2——CVE-2021-1949—5.6%
——2——CVE-2026-34553—5.6%
——2——CVE-2021-38949—5.6%
——2——CVE-2021-1917—5.6%
——2——CVE-2026-24772—5.6%
——2——CVE-2020-0313—5.6%
——2——CVE-2026-45895—5.6%
——2——CVE-2026-28985—5.5%
——2——CVE-2026-25151—5.6%
——2——CVE-2026-29496.4 MED5.6%
——2The Xpro Addons — 140+ Widgets for Elementor plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the Icon Box widget in versions up to, and including, 1.4.24 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with contributor-level access and above, to inject arbitrary web scripts in pages that will execute whenever a user accesses an injected page.8dCVE-2023-31432—5.6%
——2——CVE-2026-638837.3 HIG5.6%
——2In the Linux kernel, the following vulnerability has been resolved:
serial: qcom_geni: fix kfifo underflow when flush precedes DMA completion IRQ
When uart_flush_buffer() runs before the DMA completion IRQ is delivered,
the following race can occur (all steps serialized by uart_port_lock):
1. DMA starts: tx_remaining = N, kfifo contains N bytes
2. DMA completes in hardware; IRQ is pending but not yet delivered
3. uart_flush_buffer() acquires the port lock and calls kfifo_reset(),
making kfifo_len() = 0 while tx_remaining remains N
4. uart_flush_buffer() releases the port lock
5. DMA IRQ fires; handle_tx_dma() acquires the port lock and calls
uart_xmit_advance(uport, tx_remaining) on an empty kfifo
uart_xmit_advance() increments kfifo->out by tx_remaining. Since
kfifo_reset() already set both in and out to 0, out wraps past in,
causing kfifo_len() to return UART_XMIT_SIZE - tx_remaining. The next
start_tx_dma() call then submits a DMA transfer of stale buffer data.
Fix this by snapshotting kfifo_len() at the start of handle_tx_dma()
and skipping uart_xmit_advance() when fifo_len < tx_remaining, which
indicates the kfifo was reset by a preceding flush.5dCVE-2026-132406.5 MED5.6%
——2Missing Authorization vulnerability in Drupal Paragraphs allows Forceful Browsing. This issue affects Paragraphs versions: from 0.0.0 to 1.21.0.11d