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 845 results — Medium severityKirby CMS: CRLF injection overrides outbound HTTP headers
CVE-2026-50188 Kirby CMS: missing auth exposes restricted page titles
CVE-2026-49274 praisonai-platform: cross-tenant IDOR poisons project stats
GHSA-2fjj-qqg8-fg7x praisonaiagents: sandbox escape via format-spec read
GHSA-pv2j-rghr-v5r9 praisonaiagents: SSRF bypass via SpiderTools redirect
GHSA-6h9p-93hq-q7h6 praisonaiagents: unauth SSE endpoint enables event injection
GHSA-35w5-pcw4-jx94 marimo: reflected XSS enables JS injection in notebooks
CVE-2026-54386 open-webui: Yjs auth bypass exposes all user notes
CVE-2026-54022 open-webui: auth bypass reaches restricted Ollama backends
CVE-2026-54021 open-webui: RAG ACL bypass exposes private KB chunks
CVE-2026-54019 Open WebUI: BOLA exposes private knowledge base files
CVE-2026-54016 Open WebUI: IDOR exposes private prompt history
CVE-2026-54015 open-webui: path traversal exposes sibling dirs
CVE-2026-54014 open-webui: cross-user file read via auth bypass
CVE-2026-54009 open-webui: auth bypass allows cross-user calendar injection
CVE-2026-54006 vLLM: decompression bomb OOM via audio endpoint
CVE-2026-54233 vLLM: heap address leak enables ASLR bypass
CVE-2026-54236 vllm: EXIF/tRNS preprocessing gap enables adversarial input
GHSA-8jr5-v98p-w75m n8n: viewer role can start/cancel/delete eval workflow runs
GHSA-664h-gpgq-h6xx vLLM: image metadata mishandling corrupts multimodal inputs
CVE-2026-12491 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