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

112

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 3018 results
Severity CVE ID Summary CVSS EPSS Package Date
HIGH CVE-2026-62194 OpenClaw: privilege escalation in plugin install 8.8 0.3% openclaw Jul 13 MEDI CVE-2026-62193 OpenClaw: auth bypass in plugin install wrapper 6.5 0.2% openclaw Jul 13 HIGH CVE-2026-62192 OpenClaw: authz bypass in Discord guild actions 8.1 0.2% openclaw Jul 13 HIGH CVE-2026-62191 OpenClaw: authorization bypass in message mutations 7.1 0.2% openclaw Jul 13 HIGH CVE-2026-62190 OpenClaw: auth bypass skips agent exec approval 8.8 0.3% openclaw Jul 13 HIGH CVE-2026-62189 OpenClaw: symlink following bypasses authorization 7.1 0.2% openclaw Jul 13 HIGH CVE-2026-62188 OpenClaw Feishu: authz bypass ignores disablement 8.1 0.2% openclaw\/feishu Jul 13 HIGH CVE-2026-62187 OpenClaw Feishu: disabled accounts retain tool access 8.1 0.2% openclaw\/feishu Jul 13 HIGH CVE-2026-62186 OpenClaw: model override bypasses admin authorization 7.6 0.2% openclaw Jul 13 UNKN CVE-2026-15685 Ollama: downloadBlob array index bug enables unauth DoS — 0.4% ollama Jul 13 CRIT CVE-2026-61667 DIRAC: SQLi chained into eval() gives RCE 9.9 — DIRAC Jul 13 HIGH CVE-2026-45414 Decidim: JWT replay bypasses multi-tenant isolation 8.5 0.3% decidim Jul 13 HIGH CVE-2026-15574 vLLM Gateway: logs leak bearer tokens & chat PII 7.5 0.3% — Jul 13 MEDI E CVE-2026-15531 HashNeRF: torch.load deserialization allows local RCE 5.3 0.1% — Jul 13 MEDI E CVE-2026-15521 n8n-workflow-builder: path traversal via filePath arg 5.3 0.1% — Jul 13 CRIT CVE-2026-56271 Flowise: hardcoded JWT secrets enable full auth bypass 9.8 0.4% Flowise Jul 12 CRIT E CVE-2026-61447 PraisonAI: RCE via unsandboxed LLM code execution 10.0 0.7% praisonai Jul 11 CRIT E CVE-2026-61445 PraisonAI: AICoder root RCE via unsanitized tool calls 9.9 0.5% praisonai Jul 11 HIGH E CVE-2026-61442 PraisonAI Platform: workspace members bypass owner authz 7.1 0.3% — Jul 11 HIGH E CVE-2026-61439 PraisonAI: umbral de bloqueo mal configurado permite prompt injection 7.5 0.3% praisonai Jul 11

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