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
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 533 results — Critical severity
SeverityCVE IDSummaryCVSSEPSSPackageDate
CRITECVE-2026-39888praisonaiagents: sandbox escape enables host RCE10.00.5%praisonaiagentsApr 8CRITECVE-2026-39890PraisonAI: YAML deserialization enables unauthenticated RCE9.80.6%praisonaiApr 8CRITCVE-2026-1114lollms: weak JWT secret allows admin takeover9.80.5%lollmsApr 7CRITECVE-2026-35615PraisonAI: path traversal exposes full filesystem via agent tools—0.4%PraisonAIApr 6CRITECVE-2026-39305PraisonAI: path traversal enables arbitrary file write/RCE9.00.3%PraisonAIApr 6CRITECVE-2026-35022Claude Code: OS command injection, credential theft9.80.6%—Apr 6CRITECVE-2026-35216Budibase: Unauthenticated RCE as root via webhook9.110.9%—Apr 4CRITCVE-2026-35030LiteLLM: auth bypass via JWT cache key collision9.10.6%litellmApr 3CRITECVE-2026-0545MLflow: auth bypass in job API enables unauthenticated RCE9.14.4%mlflowApr 3CRITECVE-2026-34938praisonaiagents: sandbox bypass enables full host RCE10.013.4%praisonaiagentsApr 1CRITECVE-2026-0596MLflow: command injection via model_uri in mlserver mode9.61.4%mlflowMar 31CRITCVE-2026-33579OpenClaw: scope bypass escalates low-priv to admin9.90.8%OpenClawMar 31CRITCVE-2026-32917OpenClaw: RCE via unsanitized iMessage SCP paths9.82.0%OpenClawMar 31CRITCVE-2026-32916OpenClaw: auth bypass enables unauth agent execution9.40.5%OpenClawMar 31CRITGHSA-955r-262c-33jctelnyx: PyPI supply chain attack steals cloud creds———Mar 30CRITCVE-2026-2287CrewAI: Docker sandbox fallback enables RCE9.80.8%—Mar 30CRITCVE-2026-2286CrewAI: SSRF via unvalidated RAG tool URLs exposes internal services9.80.5%—Mar 30CRITECVE-2026-2275CrewAI: RCE via Docker fallback in CodeInterpreter9.60.5%—Mar 30CRITECVE-2025-15379MLflow: RCE via unsanitized model dependency specs10.02.4%mlflowMar 30CRITECVE-2025-15036MLflow: path traversal enables sandbox escape, file overwrite9.60.6%mlflowMar 30

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