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

2,412

AI/ML CVEs Tracked

350

Critical

293

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 851 results — Medium severity

Severity CVE ID Summary CVSS EPSS Package Date

MEDI E CVE-2025-67743 local-deep-research: SSRF allows internal network access 6.3 0.3% local-deep-research Dec 23 MEDI E CVE-2025-68477 langflow: SSRF allows internal network access 6.5 5.8% langflow Dec 19 MEDI CVE-2025-63390 anythingllm: Missing Auth allows unauthenticated access 5.3 0.5% — Dec 18 MEDI E CVE-2025-13922 AI component: SQL Injection exposes database 6.5 0.3% — Dec 6 MEDI CVE-2025-13359 taxopress: SQL Injection exposes database 6.5 0.3% — Dec 3 MEDI CVE-2025-13354 taxopress: Missing Auth allows unauthorized operations 4.3 0.2% — Dec 3 MEDI CVE-2025-62426 vllm: Resource Exhaustion enables DoS 6.5 0.3% vllm Nov 21 MEDI CVE-2025-62372 vllm: security flaw enables exploitation 6.5 0.3% vllm Nov 21 MEDI CVE-2025-12732 AI component: Info Disclosure leaks sensitive data 4.3 0.2% — Nov 12 MEDI CVE-2025-11972 AI component: SQL Injection exposes database 4.9 0.3% — Nov 8 MEDI CVE-2025-12360 Better: security flaw enables exploitation 4.3 0.2% — Nov 6 MEDI E CVE-2025-12695 dspy: security flaw enables exploitation 5.9 0.3% dspy Nov 4 MEDI E CVE-2025-12058 Keras: safe_mode bypass enables file read and SSRF — 0.2% keras Oct 29 MEDI E CVE-2025-11844 smolagents: security flaw enables exploitation 5.4 0.3% smolagents Oct 22 MEDI E CVE-2025-60511 Moodle: IDOR enables unauthorized data access 4.3 0.2% — Oct 21 MEDI CVE-2025-61620 vllm: DoS via Jinja template injection in chat API 6.5 0.2% vllm Oct 7 MEDI E CVE-2025-8917 clearml: path traversal in safe_extract → RCE risk 5.8 0.3% clearml Oct 5 MEDI E CVE-2025-55556 TensorFlow: non-deterministic compilation breaks Embedding 6.5 0.2% tensorflow Sep 25 MEDI E CVE-2025-55554 PyTorch: integer overflow in nan_to_num causes DoS 5.3 0.3% pytorch Sep 25 MEDI CVE-2025-46153 PyTorch: Dropout inconsistency enables membership inference 5.3 0.4% pytorch Sep 25

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