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 1661 results — Active exploitation
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2026-57130 PraisonAI: IMAP injection via unsanitized email tool params 8.1 0.3% praisonaiagents Sep 14 HIGH E CVE-2026-57129 PraisonAI: path traversal exposes arbitrary files 7.5 0.4% praisonaiagents Sep 14 MEDI E CVE-2026-57128 PraisonAI: SSE server auth bypass exposes config, events 4.3 0.2% praisonaiagents Sep 14 HIGH E CVE-2026-57126 PraisonAI: SpiderTools SSRF bypass via DNS resolution 8.5 0.4% praisonaiagents Sep 14 CRIT E CVE-2026-57125 PraisonAI: unauth RCE via YAML approval bypass 9.8 0.4% praisonai Sep 14 MEDI E CVE-2026-57120 PraisonAI: sandbox bypass leaks agent internals 6.5 0.3% praisonaiagents Sep 14 LOW E CVE-2026-90713 vLLM: local DoS via malformed tiktoken vocab file 3.3 0.2% vllm Sep 14 HIGH E CVE-2026-37008 CrewAI before fb2323b offers a Python blocklist... 8.1 0.1% — Sep 13 MEDI E CVE-2026-90580 Flowise: SSRF via Host/X-Forwarded-Proto in Evaluations 6.3 0.2% flowise Sep 13 HIGH E CVE-2026-90777 ESPnet: RCE via unsafe checkpoint deserialization 8.8 0.5% — Sep 13 HIGH E CVE-2026-90769 Open Notebook: SSRF via source URL hits internal services 7.7 0.3% — Sep 13 HIGH E CVE-2026-90535 Flowise: IDOR in abort API enables agent DoS 7.5 0.3% flowise Sep 12 MEDI E CVE-2026-90533 Flowise: IDOR exposes org owner's password hash 6.5 0.2% flowise Sep 12 MEDI E CVE-2026-87918 WPBot: unauthenticated AJAX abuse drains AI API budget 5.3 0.2% WPBot Sep 12 MEDI E CVE-2026-87916 WPBot: missing auth check leaks chat visitor PII 5.3 0.2% WPBot Sep 12 CRIT E CVE-2026-87987 Mistral Vibe: env-var trick bypasses command allowlist — 0.3% mistral-vibe Sep 11 HIGH E CVE-2026-71416 Headroom: CSWSH bypass allows unauthenticated LLM abuse 8.8 0.2% — Sep 11 HIGH E CVE-2026-88009 Traefik: HTTP routing desync enables auth/log bypass — 0.3% github.com/traefik/traefik/v2 Sep 10 MEDI E CVE-2026-88000 open-webui: malicious chat history causes DoS 6.5 0.3% open-webui Sep 9 MEDI E CVE-2026-88001 Open WebUI: SSRF via redirects reaches internal/metadata IPs 5.0 0.3% open-webui Sep 9

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