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 372 results — Active exploitation, has patch

Severity CVE ID Summary CVSS EPSS Package Date

CRIT E CVE-2025-4318 amplify-codegen-ui: eval injection enables build-time RCE — 0.9% @aws-amplify/codegen-ui-react Jul 30 HIGH E CVE-2026-67428 Flyto2 Core: SSRF via unvalidated URLs in agent tools 8.5 0.3% flyto-core Jul 29 HIGH E CVE-2026-67425 Flyto2 Core: SSRF leaks LLM API keys via base_url 8.6 0.3% flyto-core Jul 29 HIGH E CVE-2026-50559 Quarkus: HTTP auth bypass via %3B/%2F path smuggling 7.5 0.5% io.quarkus:quarkus-vertx-http Jul 29 HIGH E CVE-2026-54593 Pterodactyl Wings: JWT reuse enables file upload bypass 8.1 0.4% github.com/pterodactyl/wings Jul 28 HIGH E CVE-2026-61609 Pterodactyl Panel: global rate limiter enables panel-wide login DoS 7.5 0.4% pterodactyl/panel Jul 28 HIGH E CVE-2026-27775 Gitea: cached permission check allows repo takeover 8.8 0.6% code.gitea.io/gitea Jul 21 HIGH E CVE-2026-54058 Pillow: OOB read/DoS via unchecked mmap stride (McIdas) — 0.4% pillow Jul 20 HIGH E CVE-2026-12484 Keras: unsafe pickle deserialization allows RCE 7.8 0.2% keras Jul 19 MEDI E CVE-2026-54497 ViewComponent: stale context leaks admin UI cross-user 6.8 0.2% view_component Jul 15 LOW E CVE-2026-12482 Keras: symlink bypass enables tar path traversal 3.1 0.3% keras Jul 14 CRIT E CVE-2026-54069 SiYuan Note: chrome-extension origin auth bypass — 0.6% github.com/siyuan-note/siyuan/kernel Jul 10 HIGH E CVE-2026-54066 SiYuan: /assets path traversal exposes API secrets 7.5 1.9% github.com/siyuan-note/siyuan/kernel Jul 10 HIGH E CVE-2026-59221 Open WebUI: encoded path traversal in terminal proxy 7.7 0.4% open-webui Jul 9 MEDI E CVE-2026-59222 Open WebUI: channel IDOR leaks tool-server API keys — 0.3% open-webui Jul 9 LOW E CVE-2026-59215 Open WebUI: IDOR leaks private channel/DM threads 3.1 0.3% open-webui Jul 9 LOW E CVE-2026-59213 Open WebUI: cache leak exposes cross-user model lists 3.5 0.3% open-webui Jul 9 MEDI E CVE-2026-59217 Open WebUI: read-only users can inject files into RAG KBs 4.3 0.3% open-webui Jul 9 HIGH E CVE-2026-59216 Open WebUI: session hijack enables cross-user code exec 7.7 0.3% open-webui Jul 9 HIGH E CVE-2026-59219 Open WebUI: revoked JWTs bypass WebSocket auth 7.1 0.3% open-webui Jul 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