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
2,394

AI/ML CVEs Tracked

343

Critical

306

New This Week

18

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 1029 results — High severity
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2023-6015 MLflow: unauthenticated arbitrary file write via PUT 7.5 4.4% mlflow Nov 16 HIGH CVE-2023-46315 Infinite Image Browsing: path traversal leaks credentials 7.5 0.6% — Oct 22 HIGH E CVE-2023-32786 LangChain: prompt injection triggers SSRF via URL fetch 7.5 0.6% langchain Oct 20 HIGH CVE-2023-46229 LangChain: SSRF in URL loader exposes internal network 8.8 44.7% langchain Oct 19 HIGH CVE-2023-27506 Intel TF Opt: buffer overflow enables local priv-esc 7.8 0.2% optimization_for_tensorflow Aug 11 HIGH E CVE-2023-4033 MLflow: OS command injection enables local code execution 7.8 1.2% mlflow Aug 1 HIGH E CVE-2023-36189 LangChain SQLDatabaseChain: SQL injection, DB exfil 7.5 0.9% langchain Jul 6 HIGH CVE-2023-30172 MLflow: path traversal exposes arbitrary server files 7.5 1.0% mlflow May 11 HIGH E CVE-2023-27564 n8n: unauthenticated info disclosure exposes credentials 7.5 1.2% n8n May 10 HIGH E CVE-2023-27563 n8n: privilege escalation exposes full workflow admin 8.8 1.2% n8n May 10 HIGH E CVE-2023-2356 MLflow: path traversal allows unauthenticated file read 7.5 4.2% mlflow Apr 28 HIGH CVE-2023-27579 TensorFlow Lite: FPE in tflite model crashes inference runtime 7.5 0.4% tensorflow Mar 25 HIGH E CVE-2023-25801 TensorFlow: double-free in pooling ops enables RCE 7.8 0.1% tensorflow Mar 25 HIGH CVE-2023-25676 TensorFlow: NULL ptr deref DoS in ParallelConcat op 7.5 0.4% tensorflow Mar 25 HIGH CVE-2023-25675 TensorFlow XLA: Bincount shape mismatch causes DoS 7.5 0.4% tensorflow Mar 25 HIGH E CVE-2023-25674 TensorFlow: null pointer DoS in RandomShuffle (XLA) 7.5 0.4% tensorflow Mar 25 HIGH CVE-2023-25673 TensorFlow: FPE in TensorListSplit (XLA) remote DoS 7.5 0.4% tensorflow Mar 25 HIGH CVE-2023-25672 TensorFlow: NPE in LookupTableImportV2 causes DoS 7.5 0.4% tensorflow Mar 25 HIGH CVE-2023-25671 TensorFlow: OOB write DoS via integer type mismatch 7.5 0.5% tensorflow Mar 25 HIGH CVE-2023-25670 TensorFlow: null ptr DoS in quantized MKL MatMul 7.5 0.4% tensorflow Mar 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