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 1961 results — Active exploitationCVE-2026-46526local-deep-research: SSRF via URL parser differential bypass5.00.3%local-deep-researchMay 28UNKNECVE-2026-4944vllm: trust_remote_code bypass enables RCE via HuggingFace—0.7%vllmMay 28CRITECVE-2026-25879langroid: Prompt-to-SQL injection enables RCE on DB host9.80.6%langroidMay 27MEDIECVE-2026-48545Gradio: cookie injection hijacks cross-Space sessions6.80.4%gradioMay 27HIGHECVE-2026-7528Langflow: DoS via uncontrolled resource consumption7.50.3%langflowMay 27MEDIECVE-2026-9540vllm: unauthenticated DoS in OpenAI-compatible serving path5.30.4%vllmMay 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 25CRITECVE-2026-2651MLflow: auth bypass on artifact uploads enables RCE9.00.3%mlflow/mlflowMay 25CRITECVE-2026-46695Boxlite: read-only bypass enables host code execution10.00.3%boxlite-cliMay 21HIGHECVE-2026-47102LiteLLM: privilege escalation to proxy_admin via /user/update8.80.7%litellmMay 21HIGHECVE-2026-47101LiteLLM: RBAC bypass enables proxy admin escalation8.81.2%litellmMay 21HIGHECVE-2026-46519mcp-server-kubernetes: auth bypass enables full cluster RCE8.80.5%mcp-server-kubernetesMay 21HIGHECVE-2026-46517LMDeploy: hardcoded trust_remote_code enables RCE7.80.2%lmdeployMay 21HIGHECVE-2026-46432lmdeploy: hardcoded trust_remote_code enables RCE7.80.1%lmdeployMay 21MEDIECVE-2026-2734MLflow: missing authz exposes all model versions6.50.4%mlflowMay 21HIGHECVE-2026-45804diffusers: TOCTOU race bypasses trust_remote_code, RCE7.50.4%diffusersMay 20CRITECVE-2026-463399router: unauthenticated RCE exposes LLM API keys10.02.8%9routerMay 19CRITECVE-2026-2611MLflow: cross-origin bypass enables RCE via AI agent9.60.4%mlflowMay 19HIGHECVE-2026-4137MLflow: insecure tmp dir perms enable model artifact RCE7.00.2%mlflowMay 18Frequently 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