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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

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 2345 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
HIGH CVE-2026-19305 Langflow: SSRF flaw exposes internal/cloud metadata 7.5 0.3% langflow Sep 4 HIGH CVE-2026-19304 Langflow: SSRF via URL parser bypass exposes internal services 7.7 0.3% langflow Sep 4 HIGH CVE-2026-19303 Langflow: path traversal enables arbitrary file deletion 8.1 0.4% langflow Sep 4 MEDI CVE-2026-19302 Langflow: symlink flaw leaks sensitive files 6.5 0.5% langflow Sep 4 MEDI CVE-2026-19301 Langflow: SSRF allows internal network reconnaissance 6.5 0.3% langflow Sep 4 HIGH CVE-2026-19300 Langflow: leaky credential fields expose secrets 7.5 0.4% langflow Sep 4 MEDI CVE-2026-19299 Langflow: authenticated path traversal leaks files 6.5 0.5% langflow Sep 4 HIGH CVE-2026-19298 Langflow: auth bypass in flow build enables RCE 8.8 0.5% langflow Sep 4 MEDI CVE-2026-9186 Langflow: header spoof bypasses MCP config write guard 6.5 0.3% langflow Sep 4 MEDI CVE-2026-9138 Langflow: path traversal enables arbitrary file write 6.5 0.3% langflow Sep 4 MEDI CVE-2026-8447 Langflow: stored XSS in Playground chat UI 6.1 0.2% langflow Sep 4 HIGH CVE-2026-85686 ms-swift: unauth SSRF via multimodal media URLs 7.5 0.3% ms-swift Sep 4 HIGH E CVE-2026-85673 LLaMA-Factory: SSRF guard bypass via redirect/DNS rebind 7.5 0.4% llama-factory Sep 4 MEDI E CVE-2026-85670 tokenizers: malformed vocab crashes process (DoS) 6.5 0.3% tokenizers Sep 4 HIGH E CVE-2026-85666 OGX/Llama Stack: SSRF via MCP tool server_url 7.5 0.4% llama-stack Sep 4 MEDI CVE-2026-85578 SiYuan: auth bypass leaks hidden notebook files 6.5 0.3% — Sep 4 UNKN E CVE-2026-85063 csv-parse: CSV header triggers prototype pollution — 0.3% — Sep 3 HIGH CVE-2026-85180 Ollama: SSRF via unvalidated model-pull redirects 7.5 0.3% ollama Sep 3 HIGH E CVE-2026-85178 Helicone: IDOR leaks cross-tenant LLM provider keys 7.7 0.2% — Sep 3 MEDI E CVE-2026-73846 ckan-mcp-server: cache key collision enables poisoning 6.5 0.2% — Sep 3

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