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
2,404

AI/ML CVEs Tracked

347

Critical

310

New This Week

18

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 1033 results — High severity
Severity CVE ID Summary CVSS EPSS Package Date
HIGH GHSA-qwgj-rrpj-75xm PraisonAI: hardcoded approval bypass enables RCE 8.8 — PraisonAI Apr 10 HIGH E CVE-2026-40158 PraisonAI: AST sandbox bypass enables host RCE 8.6 0.2% PraisonAI Apr 10 HIGH E CVE-2026-40153 praisonaiagents: env var expansion exposes production secrets 7.4 0.3% praisonaiagents Apr 10 HIGH E CVE-2026-40149 PraisonAI: auth bypass disables agent safety controls 7.9 0.2% PraisonAI Apr 10 HIGH CVE-2026-35669 OpenClaw: privilege escalation via plugin scope bypass 8.8 0.3% OpenClaw Apr 10 HIGH CVE-2026-35668 OpenClaw: sandbox path traversal exposes agent secrets 7.7 0.4% OpenClaw Apr 10 HIGH CVE-2026-35666 OpenClaw: allowlist bypass enables arbitrary command exec 8.8 0.4% OpenClaw Apr 10 HIGH CVE-2026-35663 OpenClaw: privilege escalation to admin via backend reconnect 8.8 0.3% OpenClaw Apr 10 HIGH CVE-2026-35660 OpenClaw: auth bypass allows admin session hijacking 8.1 0.3% OpenClaw Apr 10 HIGH CVE-2026-35653 OpenClaw: auth bypass enables agent profile destruction 8.1 0.6% OpenClaw Apr 10 HIGH CVE-2026-35650 OpenClaw: env var override bypass enables code execution 7.5 0.5% OpenClaw Apr 10 HIGH CVE-2026-35643 OpenClaw: WebView bridge injection enables Android RCE 8.8 0.4% OpenClaw Apr 10 HIGH CVE-2026-35641 OpenClaw: RCE via .npmrc override in plugin install 7.8 0.1% OpenClaw Apr 10 HIGH E CVE-2026-40217 LiteLLM: RCE via bytecode rewriting in guardrails API 8.8 0.7% litellm Apr 10 HIGH E CVE-2026-40150 PraisonAIAgents: SSRF exposes cloud metadata via web_crawl 7.7 0.3% praisonaiagents Apr 9 HIGH E CVE-2026-40116 PraisonAI: unauth WebSocket drains OpenAI API credits 7.5 0.4% praisonai Apr 9 HIGH E CVE-2026-40113 PraisonAI: arg injection injects env vars into Cloud Run 8.4 0.2% praisonai Apr 9 HIGH CVE-2026-35645 OpenClaw: privilege escalation via synthetic admin session scope 8.1 0.3% OpenClaw Apr 9 HIGH CVE-2026-35639 OpenClaw: scope bypass enables admin RCE via device pairing 8.8 0.5% OpenClaw Apr 9 HIGH CVE-2026-35638 OpenClaw: priv escalation via trusted-proxy scope bypass 8.8 0.3% OpenClaw Apr 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