AI Threat AlertAI 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 1527 results — Medium severityCVE-2026-47745Shopper: auth bypass enables full checkout shutdown6.50.2%shopper/frameworkMay 29MEDICVE-2026-47742Shopper: authz bypass lets any user mutate product data6.50.2%shopper/frameworkMay 29MEDIGHSA-rf84-wr5g-m3rpCAPM3: cross-namespace auth bypass exposes K8s secrets5.5—github.com/metal3-io/cluster-api-provider-metal3May 29MEDICVE-2026-35673OpenClaw: SSRF bypass exposes private network access6.50.2%openclawMay 29MEDICVE-2026-34507OpenClaw: policy bypass enables unauthorized admin command execution5.40.1%openclawMay 29MEDICVE-2026-32906OpenClaw: privilege escalation bypasses Slack plugin approval gate4.30.2%openclawMay 29MEDIECVE-2026-46526local-deep-research: SSRF via URL parser differential bypass5.00.3%local-deep-researchMay 28MEDICVE-2026-46236Linux Kernel: DMA coherency bug in xbox_remote driver5.50.1%—May 28MEDICVE-2026-45334Kirby CMS: auth bypass leaks admin emails via content lock—0.4%getkirby/cmsMay 27MEDIECVE-2026-48545Gradio: cookie injection hijacks cross-Space sessions6.80.4%gradioMay 27MEDICVE-2026-46091Linux Kernel: DMA coherency flaw in igorplugusb driver5.50.1%—May 27MEDICVE-2026-46032Linux Kernel KVM: nSVM VMEXIT host state corruption5.50.1%—May 27MEDICVE-2026-45973Linux mlx5: RDMA hang DoS on AI training clusters5.50.2%—May 27MEDICVE-2026-45907Linux mlx5e: deadlock DoS in Mellanox NIC recovery paths5.50.1%—May 27MEDICVE-2026-3676IBM Db2 APM: DoS via query special element injection6.50.4%—May 27MEDIECVE-2026-9540vllm: unauthenticated DoS in OpenAI-compatible serving path5.30.4%vllmMay 26MEDICVE-2026-41863Spring AI: path traversal via LLM-chosen filenames6.50.4%org.springframework.ai:spring-ai-anthropicMay 26MEDIECVE-2026-9468cline-mcp-memory-bank: path traversal in memory init6.30.3%—May 25MEDIECVE-2018-25378Notebook Pro: DoS via oversized notebook name input6.20.1%—May 25MEDIECVE-2026-2734MLflow: missing authz exposes all model versions6.50.4%mlflowMay 21Frequently 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