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

3,017

AI/ML CVEs Tracked

424

Critical

114

New This Week

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 3017 results

Severity CVE ID Summary CVSS EPSS Package Date

CRIT CVE-2026-71851 crypto-js: Insufficient Entropy in Cryptographic... 9.0 — crypto-js Aug 7 HIGH CVE-2026-64636 An SQL injection vulnerability in Plesk Obsidian... 7.7 — — Aug 7 MEDI GHSA-xxpx-f366-4xpq Craft CMS:Authorization bypass: view-only... — — craftcms/cms Aug 6 HIGH CVE-2026-70636 Flowise through 3.1.4 contains an authentication... 7.5 — Flowise Aug 6 CRIT CVE-2026-67622 Flowise through 3.1.4 contains an insecure direct... 9.9 — Flowise Aug 6 HIGH CVE-2026-67621 Flowise through 3.1.4 contains a missing... 7.6 — Flowise Aug 6 MEDI CVE-2026-71433 LangGraph: Namespace prefix matching crosses... 5.3 — langgraph-checkpoint-sqlite Aug 6 HIGH CVE-2026-54763 Traefik: Incomplete fix for CVE-2026-33433 +... — 0.2% github.com/traefik/traefik/v3 Aug 6 HIGH CVE-2026-43632 llama.cpp builds b7492 through the latest b9060... 8.1 — — Aug 6 MEDI CVE-2025-9266 The Accelerate theme for WordPress is vulnerable... 4.3 — Accelerate Aug 6 HIGH CVE-2026-57819 Apache CXF allows to set a limit on the number of... 7.5 — — Aug 6 MEDI CVE-2026-19008 A vulnerability was identified in mf-yang... 6.3 0.3% — Aug 6 MEDI CVE-2026-19007 A vulnerability was determined in mf-yang... 6.3 0.2% — Aug 6 MEDI CVE-2026-19006 A vulnerability was found in mf-yang openclaw-cn... 6.3 0.2% — Aug 6 HIGH CVE-2026-69111 Milvus through 2.6.22 and 3.0.0 contains an... 7.5 0.6% — Aug 5 UNKN CVE-2026-68746 Not Failing Securely ('Failing Open')... — 0.4% — Aug 5 UNKN CVE-2026-66885 Cross-Site Request Forgery (CSRF) vulnerability... — 0.2% — Aug 5 UNKN CVE-2026-66881 Relative Path Traversal vulnerability in... — 0.4% — Aug 5 UNKN CVE-2026-66298 Origin Validation Error vulnerability in... — 0.2% — Aug 5 HIGH CVE-2026-55524 PraisonAI is a multi-agent teams system. In... 7.5 0.2% — Aug 5

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