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

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 2345 results — no patch

Severity CVE ID Summary CVSS EPSS Package Date

HIGH E CVE-2026-92983 InternLM LMDeploy through 0.17.0 in DistServe... 7.5 0.4% — Sep 17 HIGH E CVE-2026-92971 InternLM LMDeploy through 0.17.0 contains a... 7.5 0.5% — Sep 17 HIGH CVE-2026-92925 A flaw was found in Redis community. The cluster... 7.1 0.3% rhaii/vllm-rocm-rhel9 Sep 17 MEDI CVE-2026-92588 n8n is a workflow automation platform. In n8n... 4.4 0.2% — Sep 16 MEDI CVE-2026-92587 n8n is a workflow automation platform. In... 5.0 0.2% — Sep 16 HIGH CVE-2026-92786 LightGBM through 4.7.0 fails to validate child... 7.8 0.1% — Sep 16 HIGH E CVE-2026-92762 Pelican Panel versions before 1.0.0-beta35... 8.8 0.3% — Sep 16 UNKN CVE-2026-62997 Kedro-Datasets provides data connectors for... — 0.4% — Sep 16 MEDI CVE-2026-92365 A vulnerability was found in vllm-project vllm up... 4.3 0.4% — Sep 16 MEDI E CVE-2026-87959 The WPBot WordPress plugin before 8.7.6 does not... 5.4 0.2% WPBot Sep 16 MEDI CVE-2026-92220 A vulnerability was found in vllm-project vLLM... 5.3 0.5% — Sep 16 MEDI CVE-2026-92298 EspoCRM through 10.0.8 uses PHP's rand() function... 4.8 0.3% — Sep 16 MEDI CVE-2026-81926 Concrete CMS 9.4.0 through 9.5.2 did not escape... 6.1 0.4% — Sep 15 HIGH GHSA-5648-rgj9-v224 @zereight/mcp-gitlab has multiple safety-control... 8.1 — — Sep 15 LOW GHSA-rf68-8gjr-36q7 Nezha: OAuth2 redirect_uri Host header injection... — — github.com/nezhahq/nezha Sep 15 HIGH CVE-2026-18110 Concrete CMS 9 (9.0.0 through 9.5.2) does not... 7.5 0.3% — Sep 15 HIGH CVE-2026-91938 Flowise versions before 3.1.4 contain a... 7.1 0.3% — Sep 15 HIGH CVE-2026-91937 Flowise before 3.1.4 fails to sanitize the... 7.5 0.3% — Sep 15 MEDI E CVE-2026-91936 Flowise versions before 3.1.4 contain a script... 6.8 0.3% — Sep 15 HIGH E CVE-2026-91935 Flowise before 3.1.4 fails to validate baseURL... 8.3 0.3% — Sep 15

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