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
3,018

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 3018 results
Severity CVE ID Summary CVSS EPSS Package Date
MEDI CVE-2026-62208 OpenClaw: Auth header leak via MCP SSE redirects 6.5 0.3% openclaw Jul 17 HIGH CVE-2026-62207 OpenClaw: auth bypass exposes admin agent tools 8.8 0.3% openclaw Jul 17 HIGH CVE-2026-62206 OpenClaw: missing authorization in Discord moderation 7.1 0.2% openclaw Jul 17 HIGH CVE-2026-62205 OpenClaw: auth bypass in MS Teams message actions 7.1 0.2% openclaw Jul 17 HIGH CVE-2026-62203 OpenClaw: env var filter gap enables priv escalation 8.8 0.3% openclaw Jul 17 HIGH CVE-2026-62202 OpenClaw: cron isolation flaw regains denied tools 8.8 0.3% openclaw Jul 17 HIGH CVE-2026-62201 OpenClaw: exec-server bypass allows internal SSRF 7.7 0.3% openclaw Jul 17 HIGH CVE-2026-54340 H2O: HTTP/2 HPACK amplification enables DoS 7.5 0.3% h2o Jul 16 HIGH CVE-2026-44453 h2o: alloca stack overflow crashes server on request 7.5 0.3% — Jul 16 MEDI CVE-2026-44452 h2o HTTP server: NULL SNI crash causes DoS 5.9 0.3% — Jul 16 HIGH CVE-2026-44436 Quicly: QUIC DoS via oversized Connection ID overflow 7.5 0.3% — Jul 16 HIGH CVE-2026-44435 H2O/Quicly: unauthenticated QUIC DoS via assertion crash 7.5 0.3% — Jul 16 MEDI CVE-2026-44434 Quicly/H2O: on-path attacker can force QUIC resets 5.3 0.1% — Jul 16 HIGH CVE-2026-44433 Quicly/H2O: QUIC flow-control bug enables memory exhaustion DoS 7.5 0.3% — Jul 16 HIGH E CVE-2026-63086 TGI: SSRF via image_url exposes cloud metadata creds 8.6 0.3% text-generation-inference Jul 16 MEDI CVE-2026-47751 Claude Code Action: RCE via malicious PR .mcp.json config — 0.6% claude-code-action Jul 16 MEDI CVE-2026-55407 Buffa: protobuf decoder DoS via 22x memory amplification — 0.4% buffa Jul 16 MEDI CVE-2026-55406 buffa: use-after-free in Rust protobuf OwnedView type — 0.1% buffa Jul 16 MEDI CVE-2026-15610 WPBot: auth bypass burns AI API credits via RAG 4.3 0.2% wpbot Jul 16 MEDI CVE-2026-15106 WPBot: broken auth lets attackers wipe chat logs 5.3 0.3% wpbot Jul 16

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