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

2,388

AI/ML CVEs Tracked

342

Critical

358

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 1026 results — High severity

Severity CVE ID Summary CVSS EPSS Package Date

HIGH CVE-2026-48505 Filament: MFA race condition enables recovery code reuse 7.4 0.2% — Jun 22 HIGH CVE-2026-56268 Flowise: cross-workspace chatflow config disclosure 7.7 0.3% Flowise Jun 22 HIGH CVE-2026-10845 WebSphere AS: JAX-WS auth bypass, unauthorized access 7.3 0.3% — Jun 22 HIGH CVE-2026-56104 Chainlit: session hijacking via WebSocket restoration 8.2 0.3% chainlit Jun 22 HIGH CVE-2026-9029 Grafana: stored XSS in geomap bypasses CVE-2023-0507 fix 7.3 0.3% — Jun 22 HIGH E CVE-2025-71378 picklescan: detection bypass enables RCE via pickle files 8.1 0.3% picklescan Jun 21 HIGH E CVE-2025-71357 picklescan: detection bypass enables RCE via malicious models 8.1 0.2% picklescan Jun 21 HIGH E CVE-2025-71351 picklescan: scanner bypass enables RCE via pickle files — 0.4% picklescan Jun 21 HIGH E CVE-2025-71348 picklescan: scanner bypass enables supply chain RCE 8.1 0.4% picklescan Jun 21 HIGH CVE-2026-12795 litellm: auth bypass in SSO debug exposes LLM proxy 7.3 0.4% litellm Jun 21 HIGH CVE-2026-12773 litellm: auth bypass in MCP proxy, no credentials required 7.3 0.4% litellm Jun 21 HIGH CVE-2026-12771 litellm: JWT auth bypass in M2M proxy handler 7.5 0.2% litellm Jun 21 HIGH CVE-2026-12770 litellm: auth bypass in Admin Key Handler endpoint 8.8 0.2% litellm Jun 21 HIGH CVE-2026-56340 vLLM: sparse tensor DoS/memory corruption via embeddings 8.8 0.3% vllm Jun 20 HIGH GHSA-6vxv-wg6j-5qwp Gogs: XSS via outdated Jupyter renderer, account takeover — — gogs.io/gogs Jun 19 HIGH GHSA-mrvx-jmjw-vggc mcp-searxng: SSRF via DNS rebinding in web_url_read 7.1 — — Jun 19 HIGH GHSA-xcqx-9jf5-w339 mcp-searxng: DoS via unbounded URL response read 7.5 — — Jun 19 HIGH E CVE-2026-55446 Langflow: pre-auth DoS via malformed multipart boundary 7.5 0.3% langflow Jun 19 HIGH CVE-2026-54528 jupyterlab-git: excluded_paths bypass exposes secrets 7.1 — jupyterlab-git Jun 19 HIGH CVE-2026-54527 jupyterlab-git: stored XSS escalates to full RCE — — @jupyterlab/git Jun 19

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