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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1580 results — no patch CVE-2026-34505 OpenClaw: webhook rate-limit bypass enables brute-force 6.5 0.3% OpenClaw Mar 31 HIGH CVE-2026-32988 OpenClaw: sandbox escape via fs-bridge TOCTOU race 7.5 0.1% OpenClaw Mar 31 HIGH CVE-2026-32982 OpenClaw: Telegram bot token leaked in media fetch errors 7.5 0.4% OpenClaw Mar 31 MEDI CVE-2026-32977 OpenClaw: TOCTOU race condition enables sandbox file escape 6.3 0.1% OpenClaw Mar 31 MEDI CVE-2026-32976 OpenClaw: auth bypass mutates protected agent config 6.5 0.2% OpenClaw Mar 31 HIGH CVE-2026-32971 OpenClaw: approval UI spoofing enables local RCE 7.1 0.3% OpenClaw Mar 31 LOW CVE-2026-32970 OpenClaw: credential fallback bypasses local auth boundary 2.5 0.1% OpenClaw Mar 31 MEDI CVE-2026-32921 OpenClaw: script approval bypass allows code execution 6.3 0.2% OpenClaw Mar 31 HIGH CVE-2026-32920 OpenClaw: workspace plugin auto-load enables RCE 8.4 0.3% OpenClaw Mar 31 CRIT CVE-2026-32917 OpenClaw: RCE via unsanitized iMessage SCP paths 9.8 2.0% OpenClaw Mar 31 CRIT CVE-2026-32916 OpenClaw: auth bypass enables unauth agent execution 9.4 0.5% OpenClaw Mar 31 HIGH CVE-2026-4399 1millionbot Millie: Boolean prompt injection bypasses restrictions 7.5 0.3% — Mar 31 HIGH CVE-2026-5201 gdk-pixbuf: JPEG heap overflow crashes vLLM inference 7.5 1.1% rhaiis/vllm-cuda-rhel9 Mar 31 CRIT GHSA-955r-262c-33jc telnyx: PyPI supply chain attack steals cloud creds — — — Mar 30 HIGH E CVE-2026-29872 awesome-llm-apps MCP Agent: cross-session credential theft 8.2 0.3% — Mar 30 CRIT CVE-2026-2287 CrewAI: Docker sandbox fallback enables RCE 9.8 0.7% — Mar 30 CRIT CVE-2026-2286 CrewAI: SSRF via unvalidated RAG tool URLs exposes internal services 9.8 0.5% — Mar 30 HIGH CVE-2026-2285 CrewAI: arbitrary file read via JSON loader tool 7.5 0.6% — Mar 30 CRIT E CVE-2026-2275 CrewAI: RCE via Docker fallback in CodeInterpreter 9.6 0.4% — Mar 30 HIGH CVE-2026-5121 libarchive: integer overflow in zisofs hits vllm containers 7.5 1.1% rhaiis/vllm-cuda-rhel9 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