Live CVE & 0day intelligence

Sound the depths of every vulnerability.

Newly released CVEs across every platform — sleek to read, verbose on demand, and served raw as markdown for AI and agent ingestion. Severity reads as depth: the deeper the contact, the graver the threat.

Browse the feed For agents → /llms.txt

Depth = severity + exploitation

HadalCritical and actively exploited (CISA KEV / 0day)
AbyssalCritical with a public exploit or in-the-wild use
MidnightCritical, or high with PoC / in-the-wild
TwilightHigh severity, or a signal on a lesser flaw
SunlitLow / medium · no exploitation signal

69475

Tracked CVEs

6472

Critical

736

Exploited in wild

3729

Last 7 days

Trending now

Bluesky + Hacker News mentions, last 7 days

1CVE-2026-109618Critical· 9.2RCE via OOM corruption4896
2CVE-2026-109619Critical· 9.2RCE via stale global state2196
3CVE-2026-111497Critical· 9.2Out-of-Bounds Write in Google Brotli Decoder1592
4CVE-2026-99999Critical· 9.3In the Linux kernel, the following vulnerability has been resolved: ipv4: validate checksum_start before completing checksum If a packet with bad checksum metadata gets into the ipv4 stack, skb_checksum_help can corrupt the network hea…963
5CVE-2026-110264Critical· 10.0Integer Overflow or Wraparound in GitLab267
6CVE-2026-108707Critical· 9.8Wukong_HRM through commit 186115e contains an authentication bypass vulnerability in ParamAspect that allows unauthenticated attackers to call every HRM API endpoint by omitting the AUTH-TOKEN header266
7CVE-2026-91403Critical· 9.1Vulnerability in the Oracle Java SE, Oracle GraalVM for JDK, Oracle GraalVM Enterprise Edition product of Oracle Java SE (component: JSSE)262

This week's digest →All digests

Feed

11 matches

CVE-2026-55615Critical

3mo ago

Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

▾ Midnightlangroid · langroidEPSS 0.46%via GHSA

CVE-2026-54760Critical

3mo ago

Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls

▾ Midnightlangroid · langroidEPSS 0.65%via GHSA

CVE-2026-54769Critical· 10.0

3mo ago

Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent

▾ Midnightlangroid · langroidEPSS 0.91%via GHSA

CVE-2026-54771High· 8.1

3mo ago

Langroid: handle_message() executes user-supplied tool JSON without sender verification

▾ Twilightlangroid · langroidEPSS 0.39%via GHSA

CVE-2026-50180High

4mo ago

Langroid: SQLChatAgent _validate_query blocklist misses pg_read_file family enabling arbitrary file read

▾ Twilightlangroid · langroidEPSS 0.69%via GHSA

CVE-2026-50181High· 7.1PoC

4mo ago

Langroid: Path traversal in the file tools allows read/write outside configured current directory

▾ Midnightlangroid · langroidEPSS 0.18%via GHSA

CVE-2026-25879Critical· 9.8

5mo ago

Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

▾ Twilightlangroid · langroidEPSS 0.53%via OSV

CVE-2025-46726High

1y ago

Langroid Allows XXE Injection via XMLToolMessage

▾ Twilightlangroid · langroidEPSS 0.65%via OSV

From the blog

All posts →

Oct 27, 2026

VulnSea has moved to vulnsea.com (and what changed since September)

The beta is over. VulnSea now runs at vulnsea.com, every old beta link redirects to the same page, and your account, API keys and watchlists came with it. Plus a round of hardening, faster pages, and new request limits agents should know about.

Sep 8, 2026

What's new: open corpus, three new MCP tools, vendor advisories, package pages

A summary of everything that shipped over the last two weeks — the whole corpus is open, agents get change feeds, alias resolution and EPSS movers, and the data now includes CVE.org, vendor CSAF, aggregated exploits and per-source scores.

Jul 1, 2026

Wiring VulnSea into an agent: a hands-on tutorial

A step-by-step guide to plugging VulnSea into automated and agentic workflows — poll the delta, triage without burning tokens, match an SBOM, and let an MCP-native model do the reasoning.

Sound the depths of every vulnerability.

Trending now

Feed

Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls

Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent

Langroid: handle_message() executes user-supplied tool JSON without sender verification

Langroid: SQLChatAgent _validate_query blocklist misses pg_read_file family enabling arbitrary file read

Langroid: Path traversal in the file tools allows read/write outside configured current directory

Langroid has Prompt to SQL Injection, Leading to RCE

Langroid has WAF Bypass Leading to RCE in TableChatAgent

Langroid has a Code Injection vulnerability in TableChatAgent

Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

Langroid Allows XXE Injection via XMLToolMessage

From the blog

VulnSea has moved to vulnsea.com (and what changed since September)

What's new: open corpus, three new MCP tools, vendor advisories, package pages

Wiring VulnSea into an agent: a hands-on tutorial

Sound the depths of every vulnerability.

Trending now

Feed

Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls

Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent

Langroid: handle_message() executes user-supplied tool JSON without sender verification

Langroid: SQLChatAgent _validate_query blocklist misses pg_read_file family enabling arbitrary file read

Langroid: Path traversal in the file tools allows read/write outside configured current directory

Langroid has Prompt to SQL Injection, Leading to RCE

Langroid has WAF Bypass Leading to RCE in TableChatAgent

Langroid has a Code Injection vulnerability in TableChatAgent

Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

Langroid Allows XXE Injection via XMLToolMessage

From the blog

VulnSea has moved to vulnsea.com (and what changed since September)

What's new: open corpus, three new MCP tools, vendor advisories, package pages

Wiring VulnSea into an agent: a hands-on tutorial