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
4,330

AI/ML CVEs Tracked

535

Critical

107

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4330 results
SeverityCVE IDSummaryCVSSEPSSPackageDate
HIGHCVE-2026-32982OpenClaw: Telegram bot token leaked in media fetch errors7.50.4%OpenClawMar 31MEDICVE-2026-32977OpenClaw: TOCTOU race condition enables sandbox file escape6.30.1%OpenClawMar 31MEDICVE-2026-32976OpenClaw: auth bypass mutates protected agent config6.50.2%OpenClawMar 31HIGHCVE-2026-32971OpenClaw: approval UI spoofing enables local RCE7.10.3%OpenClawMar 31LOWCVE-2026-32970OpenClaw: credential fallback bypasses local auth boundary2.50.1%OpenClawMar 31MEDICVE-2026-32921OpenClaw: script approval bypass allows code execution6.30.2%OpenClawMar 31HIGHCVE-2026-32920OpenClaw: workspace plugin auto-load enables RCE8.40.3%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 31HIGHCVE-2026-43991millionbot Millie: Boolean prompt injection bypasses restrictions7.50.3%—Mar 31HIGHCVE-2026-5201gdk-pixbuf: JPEG heap overflow crashes vLLM inference7.51.1%rhaiis/vllm-cuda-rhel9Mar 31CRITGHSA-955r-262c-33jctelnyx: PyPI supply chain attack steals cloud creds———Mar 30HIGHGHSA-m3mh-3mpg-37hwOpenClaw: .npmrc hijack enables RCE on plugin install8.6—openclawMar 30MEDIGHSA-68f8-9mhj-h2mpOpenClaw: HTTP scope bypass enables model enumeration——openclawMar 30HIGHGHSA-hr5v-j9h9-xjhgOpenClaw: sandbox escape via mediaUrl path traversal7.7—openclawMar 30HIGHECVE-2026-29872awesome-llm-apps MCP Agent: cross-session credential theft8.20.3%—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 30HIGHCVE-2026-2285CrewAI: arbitrary file read via JSON loader tool7.50.6%—Mar 30CRITECVE-2026-2275CrewAI: RCE via Docker fallback in CodeInterpreter9.60.5%—Mar 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