AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
4,330

AI/ML CVEs Tracked

535

Critical

107

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4330 results
HIGH

OpenClaw: auth bypass in MS Teams message actions

CVE-2026-62205
7.1
EPSS 0.4%
Auth BypassAgentPlugin
openclawCWE-86232 ATLAS
HIGH

OpenClaw: env var filter gap enables priv escalation

CVE-2026-62203
8.8
EPSS 0.5%
Auth BypassCode ExecutionAgent
openclawCWE-18433 ATLAS
HIGH

OpenClaw: cron isolation flaw regains denied tools

CVE-2026-62202
8.8
EPSS 0.5%
Auth BypassCode ExecutionAgentPlugin
openclawCWE-86333 ATLAS
HIGH

OpenClaw: exec-server bypass allows internal SSRF

CVE-2026-62201
7.7
EPSS 0.4%
Auth BypassData LeakageAgentPlugin
openclawCWE-91833 ATLAS
HIGH

H2O: HTTP/2 HPACK amplification enables DoS

CVE-2026-54340
7.5
EPSS 0.5%
DoSInferenceAPI
h2oCWE-400272 ATLAS
HIGH

h2o: alloca stack overflow crashes server on request

CVE-2026-44453
7.5
EPSS 0.5%
DoSInference
CWE-7702 ATLAS
MEDIUM

h2o HTTP server: NULL SNI crash causes DoS

CVE-2026-44452
5.9
EPSS 0.4%
DoSAPI
CWE-1251 ATLAS
HIGH

Quicly: QUIC DoS via oversized Connection ID overflow

CVE-2026-44436
7.5
EPSS 0.5%
DoSInferenceAPI
CWE-1201 ATLAS
HIGH

H2O/Quicly: unauthenticated QUIC DoS via assertion crash

CVE-2026-44435
7.5
EPSS 0.5%
DoSAPIInference
CWE-4002 ATLAS
MEDIUM

Quicly/H2O: on-path attacker can force QUIC resets

CVE-2026-44434
5.3
EPSS 0.2%
DoSInference
CWE-3451 ATLAS
HIGH

Quicly/H2O: QUIC flow-control bug enables memory exhaustion DoS

CVE-2026-44433
7.5
EPSS 0.5%
DoSAPI
CWE-4001 ATLAS
HIGHEXPLOIT AVAIL

TGI: SSRF via image_url exposes cloud metadata creds

CVE-2026-63086
8.6
EPSS 0.4%
Data ExtractionAuth BypassInferenceAPI
text-generation-inferenceCWE-9184 ATLAS
MEDIUM

Claude Code Action: RCE via malicious PR .mcp.json config

CVE-2026-47751
--
EPSS 0.8%
Supply ChainCode ExecutionData LeakageAgentPlugin
claude-code-action5 ATLAS
MEDIUM

Buffa: protobuf decoder DoS via 22x memory amplification

CVE-2026-55407
--
EPSS 0.8%
DoSInferenceAPI
buffa6.3K2 ATLAS
MEDIUM

buffa: use-after-free in Rust protobuf OwnedView type

CVE-2026-55406
--
EPSS 0.2%
Data LeakageCode ExecutionInferenceAPI
buffa6.3K1 ATLAS
MEDIUM

WPBot: auth bypass burns AI API credits via RAG

CVE-2026-15610
4.3
EPSS 0.4%
Auth BypassDoSPluginRAG
wpbotCWE-8624 ATLAS
MEDIUM

WPBot: broken auth lets attackers wipe chat logs

CVE-2026-15106
5.3
EPSS 0.5%
Auth BypassPluginAgent
wpbotCWE-8621 ATLAS
HIGH

Feast: unauth WebSocket connections cause DoS

CVE-2026-23538
7.5
EPSS 0.9%
DoSAuth BypassFrameworkInference
rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel91.9K2 ATLAS
MEDIUMEXPLOIT AVAIL

ViewComponent: stale context leaks admin UI cross-user

CVE-2026-54497
6.8
EPSS 0.3%
Auth BypassData LeakageFramework
view_componentPatch: 4.12.0CWE-362514
CRITICALEXPLOIT AVAIL

AVideo: stored XSS in YPTSocket enables admin takeover

CVE-2026-54458
9.6
EPSS 0.4%
Code ExecutionAuth BypassData LeakagePlugin
CWE-791 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial