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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1052 results — Medium severity GHSA-r48f-3986-4f9c fickling: Allowlist Bypass evades input filtering — — fickling Mar 13 MEDI CVE-2026-32061 OpenClaw: $include path traversal exposes secrets 4.4 0.1% openclaw Mar 11 MEDI CVE-2026-2589 Greenshift: Info Disclosure leaks sensitive data 5.3 0.2% — Mar 6 MEDI CVE-2026-28277 langgraph: Deserialization enables RCE 6.8 4.9% langgraph Mar 5 MEDI CVE-2026-28415 gradio: Info Disclosure leaks sensitive data 4.7 0.2% gradio Feb 27 MEDI E CVE-2026-27167 gradio: Weak Credentials allow account compromise 5.9 0.5% gradio Feb 27 MEDI CVE-2026-27578 n8n: XSS enables session hijacking 5.4 0.2% n8n Feb 25 MEDI CVE-2026-27794 langgraph-checkpoint: Deserialization enables RCE 6.6 0.7% langgraph-checkpoint Feb 25 MEDI GHSA-mhc9-48gj-9gp3 fickling: Allowlist Bypass evades input filtering — — fickling Feb 25 MEDI E CVE-2026-27482 ray: Missing Auth allows unauthenticated access 5.9 0.3% ray Feb 20 MEDI CVE-2026-26972 OpenClaw: path traversal allows arbitrary file write 6.7 0.2% openclaw Feb 20 MEDI CVE-2026-26320 OpenClaw: UI deception enables arbitrary command execution 6.5 0.4% openclaw Feb 19 MEDI CVE-2025-12343 ffmpeg: security flaw enables exploitation 5.5 0.1% — Feb 18 MEDI CVE-2026-26019 langchain_community: SSRF allows internal network access 4.1 0.4% langchain_community Feb 11 MEDI CVE-2025-14831 GnuTLS: TLS cert parsing DoS hits vllm inference 5.3 0.6% rhaiis/vllm-cuda-rhel9 Feb 9 MEDI CVE-2026-25631 n8n: Input Validation flaw enables exploitation 6.5 0.3% n8n Feb 6 MEDI CVE-2026-25640 pydantic-ai: Path Traversal enables file access 5.4 0.3% pydantic-ai-slim Feb 6 MEDI E CVE-2026-25475 OpenClaw: path traversal enables arbitrary file read 6.5 0.7% openclaw Feb 4 MEDI CVE-2026-25054 n8n: XSS enables session hijacking 5.4 0.2% n8n Feb 4 MEDI CVE-2026-25051 n8n: XSS enables session hijacking 5.4 0.2% n8n Feb 4 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