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

2,405

AI/ML CVEs Tracked

347

Critical

310

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 1033 results — High severity

Severity CVE ID Summary CVSS EPSS Package Date

HIGH GHSA-5r2p-pjr8-7fh7 sagemaker: Allowlist Bypass evades input filtering — — sagemaker Mar 5 HIGH CVE-2026-25048 xgrammar: security flaw enables exploitation — 0.4% xgrammar Mar 5 HIGH CVE-2026-25750 langsmith: security flaw enables exploitation 8.1 0.3% langsmith Mar 4 HIGH GHSA-5hwf-rc88-82xm fickling: Allowlist Bypass evades input filtering — — fickling Mar 4 HIGH GHSA-wccx-j62j-r448 fickling: Protection Bypass circumvents security controls — — fickling Mar 4 HIGH CVE-2026-0847 NLTK: path traversal exposes sensitive server files 8.6 0.7% — Mar 4 HIGH E CVE-2026-27905 bentoml: security flaw enables exploitation 7.8 0.3% bentoml Mar 3 HIGH E CVE-2026-28416 gradio: SSRF allows internal network access 8.6 0.3% gradio Feb 27 HIGH E CVE-2026-28414 gradio: security flaw enables exploitation 7.5 3.1% gradio Feb 27 HIGH CVE-2026-27498 n8n: Code Injection enables RCE 8.8 0.7% n8n Feb 25 HIGH CVE-2026-27497 n8n: SQL Injection exposes database 8.8 0.8% n8n Feb 25 HIGH CVE-2026-27795 LangChain: SSRF allows internal network access 7.4 0.2% — Feb 25 HIGH GHSA-mxhj-88fx-4pcv fickling: security flaw enables exploitation — — fickling Feb 24 HIGH CVE-2026-2033 mlflow: Path Traversal enables file access 8.1 1.8% mlflow Feb 20 HIGH CVE-2026-2472 google-cloud-aiplatform: XSS enables session hijacking — 0.5% google-cloud-aiplatform Feb 20 HIGH CVE-2026-27001 OpenClaw: prompt injection via unsanitized workspace path 7.8 0.2% openclaw Feb 20 HIGH CVE-2026-26321 OpenClaw: path traversal enables local file exfiltration 7.5 0.5% openclaw Feb 19 HIGH E CVE-2026-26286 sillytavern: SSRF allows internal network access 8.5 0.3% — Feb 19 HIGH GHSA-97f8-7cmv-76j2 picklescan: Allowlist Bypass evades input filtering — — picklescan Feb 18 HIGH CVE-2026-1669 keras: File Control enables path manipulation 7.5 0.3% keras Feb 11

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