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 826 results — has patch GHSA-364x-8g5j-x2pr n8n: stored XSS via malicious OAuth2 Authorization URL 5.4 — n8n Mar 27 MEDI GHSA-3c7f-5hgj-h279 n8n: Stored XSS in Chat Trigger via CSS injection 5.4 — n8n Mar 27 MEDI GHSA-w673-8fjw-457c n8n: stored XSS enables phishing via Form Node 4.1 — n8n Mar 27 MEDI GHSA-q4fm-pjq6-m63g n8n: Stored XSS in Form Trigger enables phishing 5.4 — n8n Mar 27 LOW E CVE-2026-29071 Open WebUI: IDOR exposes AI memories and private files 3.1 0.3% open-webui Mar 27 MEDI E CVE-2026-29070 open-webui: missing authz allows cross-KB file deletion 5.4 0.3% open-webui Mar 27 HIGH E CVE-2026-28788 Open WebUI: BOLA enables RAG poisoning via file overwrite 7.1 2.9% open-webui Mar 27 MEDI E CVE-2026-28786 Open WebUI: path traversal leaks server filesystem path 4.3 0.4% open-webui Mar 27 HIGH E CVE-2026-33744 BentoML: command injection in bentofile.yaml containerize 7.8 0.3% bentoml Mar 27 HIGH CVE-2026-27893 vLLM: trust_remote_code bypass enables RCE 8.8 0.7% vllm Mar 27 MEDI CVE-2026-33682 Streamlit: SSRF leaks NTLMv2 creds via UNC path 4.7 0.3% Streamlit Mar 26 MEDI CVE-2026-33751 n8n: LDAP injection enables auth bypass in workflows 4.8 0.2% n8n Mar 25 CRIT CVE-2026-33749 n8n: stored XSS enables credential theft via workflow 9.0 0.2% n8n Mar 25 HIGH CVE-2026-33724 n8n: SSH MitM enables malicious workflow injection 7.4 0.3% n8n Mar 25 MEDI CVE-2026-33722 n8n: secrets vault bypass exposes credentials to low-priv users 5.3 0.3% n8n Mar 25 MEDI CVE-2026-33720 n8n: OAuth state forgery hijacks user credentials 4.2 0.2% n8n Mar 25 HIGH CVE-2026-33713 n8n: SQLi in Data Table node, full DB compromise 8.8 0.4% n8n Mar 25 HIGH CVE-2026-33696 n8n: Prototype pollution enables RCE via workflow nodes 8.8 0.8% n8n Mar 25 HIGH CVE-2026-33665 n8n: LDAP email match enables permanent account takeover 8.2 0.3% n8n Mar 25 CRIT CVE-2026-33663 n8n: member role steals plaintext HTTP credentials 10.0 0.4% n8n 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