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

3,018

AI/ML CVEs Tracked

424

Critical

113

New This Week

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 3018 results

Severity CVE ID Summary CVSS EPSS Package Date

MEDI CVE-2026-54020 Open WebUI: DNS Rebinding SSRF Bypass 6.3 0.2% open-webui Aug 4 MEDI CVE-2026-70487 Open WebUI: Cross-user file content disclosure... 5.3 0.3% open-webui Aug 4 MEDI CVE-2026-70488 Open WebUI: Deletion of directories and file... 4.3 0.2% open-webui Aug 4 HIGH CVE-2026-70486 Open WebUI: Same-origin XSS to account takeover... 8.2 0.4% open-webui Aug 4 HIGH CVE-2026-70485 Open WebUI: Any authenticated user can reach... 7.1 0.2% open-webui Aug 4 MEDI CVE-2026-70484 Open WebUI: Users denied the image-generation... 4.3 0.3% open-webui Aug 4 MEDI CVE-2026-70480 Open WebUI: Client-side SSRF via unrestricted... 4.1 0.2% open-webui Aug 4 LOW CVE-2026-70483 Open WebUI: Any authenticated user can cancel... 3.1 0.2% open-webui Aug 4 HIGH CVE-2026-70482 Open WebUI: Account takeover via OAuth token... 8.1 0.3% open-webui Aug 4 MEDI CVE-2026-70481 Open WebUI: Any member with write access to a... 5.4 0.3% open-webui Aug 4 HIGH CVE-2026-70479 Open WebUI: SSRF into internal services via... 7.7 0.3% open-webui Aug 4 CRIT CVE-2026-70478 Flowise: Unauthenticated OAuth2 token refresh... — 0.4% flowise Aug 4 UNKN CVE-2026-70477 Flowise: CSV Agent Prompt Injection Remote Code... — 0.4% flowise-components Aug 4 UNKN CVE-2026-70476 Flowise: Broken Access Control in Stripe... — 0.3% flowise Aug 4 MEDI GHSA-8gj2-2cvc-6xx7 Flowise: Unauthenticated Credential Abuse via... — — flowise Aug 4 UNKN CVE-2026-70475 Flowise: Missing Authorization on Execution... — 0.3% flowise Aug 4 HIGH CVE-2026-70474 Flowise: Cross-Workspace OAuth2 Credential... — 0.3% flowise Aug 4 MEDI GHSA-rwrp-9823-p2xq Flowise: Incomplete Credential Redaction Exposes... 6.5 — flowise Aug 4 UNKN CVE-2026-70473 Flowise: Information Disclosure in GET... — 0.2% flowise Aug 4 HIGH CVE-2026-70472 Flowise: Cross-workspace credential IDOR in... — 0.2% flowise Aug 4

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