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
2,377

AI/ML CVEs Tracked

340

Critical

392

New This Week

18

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 1069 results — Active exploitation
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2026-45401 open-webui: SSRF redirect bypass exposes internal services 8.5 0.2% open-webui May 14 HIGH E CVE-2026-45400 open-webui: SSRF bypass via URL parser mismatch 8.5 0.2% open-webui May 14 HIGH E CVE-2026-45399 Open WebUI: task auth bypass enables cross-user DoS 7.1 0.3% open-webui May 14 HIGH E CVE-2026-45398 open-webui: IDOR exposes private RAG knowledge bases 7.5 0.3% open-webui May 14 MEDI E CVE-2026-45397 Open WebUI: unauthenticated RAG config leaks AI pipeline 5.3 0.6% open-webui May 14 MEDI E CVE-2026-45396 open-webui: mass assignment enables leaderboard poisoning 5.4 0.3% open-webui May 14 MEDI E CVE-2026-45387 open-webui: system prompt leakage via model read API 4.3 0.2% open-webui May 14 MEDI E CVE-2026-45386 open-webui: auth bypass lets read-only users pin messages 4.3 0.2% open-webui May 14 MEDI E CVE-2026-45385 Open WebUI: IDOR lets members tamper with admin messages 4.3 0.2% open-webui May 14 MEDI E CVE-2026-45365 open-webui: auth bypass exposes admin-restricted models 5.4 0.2% open-webui May 14 MEDI E CVE-2026-45351 Open WebUI: admin system prompts exposed to all users 6.5 0.3% open-webui May 14 HIGH E CVE-2026-45350 open-webui: missing authz allows admin tool hijacking 7.1 0.3% open-webui May 14 HIGH E CVE-2026-45349 open-webui: auth bypass exposes all user chat histories 7.1 0.2% open-webui May 14 MEDI E CVE-2026-45347 Open WebUI: blind SSRF via PDF export HTML injection 4.3 0.2% open-webui May 14 MEDI E CVE-2026-45345 open-webui: IDOR allows unauthorized model modification 6.5 0.2% open-webui May 14 MEDI E CVE-2026-45339 Open WebUI: API key restriction bypass via header swap 6.5 0.3% open-webu May 14 HIGH E CVE-2026-45338 open-webui: SSRF via OAuth picture claim leaks internal data 7.7 0.4% open-webui May 14 HIGH E CVE-2026-45331 open-webui: SSRF bypass exposes cloud IAM credentials 8.5 0.3% open-webui May 14 MEDI E CVE-2026-45317 Open-WebUI: CSRF image URL leaks session cookies 4.6 0.2% open-webui May 14 MEDI E CVE-2026-45318 open-webui: Stored XSS via Office file preview bypass 5.4 0.2% open-webui May 14

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