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
3,018

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 1942 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
CRIT E CVE-2026-65700 h2oGPT: unauth path traversal in files API leads to RCE 9.8 1.3% h2ogpt Jul 23 HIGH E CVE-2026-65917 CyberPanel: IDOR exposes cross-tenant backups 8.8 0.4% — Jul 23 MEDI E CVE-2026-65012 InvokeAI: unauthenticated directory enumeration flaw 5.3 0.3% invokeai Jul 22 HIGH CVE-2026-64832 FFmpeg: double-free in NVDEC decoder enables RCE 8.8 0.3% — Jul 22 HIGH CVE-2026-65315 Ollama: crafted GGUF file crashes inference server 7.5 0.6% ollama Jul 21 MEDI CVE-2026-60152 PeopleSoft: unauthorized data access via Panel Processor 5.4 0.2% — Jul 21 MEDI CVE-2026-47024 PeopleSoft PeopleTools: CSRF-style data tampering flaw 5.4 0.2% — Jul 21 HIGH E CVE-2026-63764 lmdeploy: SSRF via redirect bypasses private IP guard 8.6 0.3% lmdeploy Jul 21 MEDI CVE-2026-63092 Kirby Modules: license key disclosure via activate dialog 4.3 0.2% — Jul 21 HIGH E CVE-2026-47237 Kubeflow: token theft lets any user hijack accounts 8.0 0.3% — Jul 21 HIGH CVE-2026-15829 MCP Toolbox: SQLi bypasses BigQuery allowedDatasets ACL — 0.2% — Jul 21 CRIT E CVE-2026-65007 Grav CMS API plugin: forged keys enable account takeover 9.6 0.3% — Jul 21 MEDI E CVE-2026-14185 WPBot: missing auth check lets subscribers edit RAG config 4.3 0.2% — Jul 21 UNKN E CVE-2026-57495 AgenticMail: unauthenticated email hijacks AI agent — 0.3% — Jul 20 MEDI CVE-2026-64650 @ai-sdk/harness-codex: tool relay authz bypass — 0.1% — Jul 20 CRIT E CVE-2026-63766 GPT-SoVITS: unauthenticated RCE via webui.py 9.8 1.7% — Jul 20 CRIT CVE-2026-63767 ktransformers: unauth pickle RCE via ZMQ socket 9.8 0.7% ktransformers Jul 20 MEDI CVE-2026-46671 onenote_parser: path traversal via crafted .onetoc2 file 4.4 0.1% — Jul 20 UNKN E CVE-2026-12228 Lollms: stored XSS in prompt-share DM inbox — 0.3% parisneo/lollms Jul 18 HIGH CVE-2026-50272 dd-trace: unbounded W3C baggage parsing enables DoS 7.5 0.4% — Jul 17

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