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-2026-54022open-webui: Yjs auth bypass exposes all user notes5.30.3%open-webuiJun 17MEDICVE-2026-54021open-webui: auth bypass reaches restricted Ollama backends6.30.3%open-webuiJun 17MEDIECVE-2026-54019open-webui: RAG ACL bypass exposes private KB chunks6.50.4%open-webuiJun 17MEDIECVE-2026-54016Open WebUI: BOLA exposes private knowledge base files4.30.3%open-webuiJun 17MEDIECVE-2026-54015Open WebUI: IDOR exposes private prompt history6.40.3%open-webuiJun 17MEDIECVE-2026-54014open-webui: path traversal exposes sibling dirs4.30.4%open-webuiJun 17MEDIECVE-2026-54009open-webui: cross-user file read via auth bypass6.50.4%open-webuiJun 17MEDIECVE-2026-54006open-webui: auth bypass allows cross-user calendar injection4.30.3%open-webuiJun 17MEDICVE-2026-54233vLLM: decompression bomb OOM via audio endpoint6.50.4%vllmJun 17MEDIECVE-2026-54236vLLM: heap address leak enables ASLR bypass5.30.9%vllmJun 17MEDIGHSA-8jr5-v98p-w75mvllm: EXIF/tRNS preprocessing gap enables adversarial input4.8—vllmJun 17MEDICVE-2026-54235vLLM: NaN/Inf bypass crashes GPU inference workers6.50.4%vllmJun 17MEDIGHSA-664h-gpgq-h6xxn8n: viewer role can start/cancel/delete eval workflow runs5.4—n8nJun 17MEDICVE-2026-12491vLLM: image metadata mishandling corrupts multimodal inputs4.80.2%rhaiis/vllm-cpu-rhel9Jun 17MEDICVE-2026-54314n8n: decompression bomb DoS via public webhook—0.5%n8nJun 16MEDICVE-2026-48782pydantic-ai: SSRF IPv6 bypass exposes cloud IAM creds6.80.4%pydantic-aiJun 16MEDIGHSA-h3jj-5f3v-3685n8n: read-only users can trigger workflow execution via API6.4—n8nJun 16MEDIGHSA-jwm3-qcfw-c5ppn8n: AST bypass leaks env vars in Python Task Runner5.0—n8nJun 16MEDICVE-2026-54303n8n: reflected XSS in trigger nodes enables session hijack—0.2%n8nJun 16MEDICVE-2026-48776LangGraph SDK: path traversal bypasses proxy-layer authz4.20.2%langchain-aiJun 16Frequently 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