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 1942 results — no patch CVE-2026-67338 JupyterLab before 4.5.9 contains a stored... 6.1 0.2% — Aug 1 CRIT CVE-2026-68771 ComfyUI: unauthenticated RCE via pickle upload 9.8 0.6% — Jul 31 CRIT CVE-2026-68770 sentence-transformers: trust gate bypass enables RCE 9.8 0.5% sentence-transformers Jul 31 HIGH CVE-2026-52856 Pterodactyl Wings: SFTP handshake DoS via Go panic 7.5 0.3% — Jul 31 MEDI CVE-2026-52857 Pterodactyl Wings: config parser DoS exhausts memory 5.5 0.1% — Jul 31 MEDI CVE-2026-17350 pgAdmin: broken access control bypasses tool permissions 5.4 0.2% — Jul 31 MEDI GHSA-xrmj-5g4g-8987 Dynatrace MCP: Jinja injection creates persistent exfil 4.2 — — Jul 31 MEDI GHSA-pqh8-p93p-2rx7 Dynatrace MCP server: DQL injection bypasses read-tool caps 4.3 — — Jul 31 MEDI CVE-2026-44615 Apache Zeppelin: path traversal escapes notebook root 6.5 0.5% — Jul 31 HIGH CVE-2026-14538 Google mcp-toolbox: BigQuery allowedDatasets bypass 7.7 0.2% — Jul 31 CRIT E CVE-2026-66421 OpenClaw Dashboard: stored XSS enables admin takeover 9.3 0.4% openclaw-dashboard Jul 30 HIGH CVE-2026-66420 MeshCentral: origin-check bypass lets attackers hijack admin sessions 8.8 0.2% openclaw-dashboard Jul 30 CRIT E CVE-2026-66418 OpenClaw: stored XSS via login field hijacks admin 9.3 0.3% openclaw Jul 30 CRIT CVE-2026-12946 Langflow: unsanitized code input enables RCE 9.9 0.4% langflow Jul 30 CRIT E CVE-2026-15976 SGLang: RCE via unsafe pickle deserialization on weight load 9.8 0.3% — Jul 30 HIGH CVE-2026-13444 Langflow: IDOR exposes/poisons cross-tenant RAG vectors 8.1 0.2% langflow Jul 30 HIGH CVE-2026-12945 Langflow: IDOR exposes/manipulates other users' builds 7.1 0.2% langflow Jul 30 CRIT CVE-2026-12940 Langflow: unauth RCE via MCP env var injection 9.8 0.5% langflow Jul 30 MEDI CVE-2026-10700 Langflow: IDOR in file API leaks cross-tenant data 6.5 0.4% Langflow OSS Jul 30 CRIT CVE-2026-13435 Langflow: PythonREPL sandbox escape enables RCE 9.9 0.3% Langflow OSS Jul 30 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