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 1052 results — Medium severity GHSA-pv2j-rghr-v5r9 praisonaiagents: sandbox escape via format-spec read 6.5 — praisonaiagents Jun 18 MEDI GHSA-6h9p-93hq-q7h6 praisonaiagents: SSRF bypass via SpiderTools redirect 6.5 — praisonaiagents Jun 18 MEDI GHSA-35w5-pcw4-jx94 praisonaiagents: unauth SSE endpoint enables event injection 4.3 — praisonaiagents Jun 18 MEDI CVE-2026-54386 marimo: reflected XSS enables JS injection in notebooks 6.1 0.2% marimo Jun 17 MEDI E CVE-2026-54022 open-webui: Yjs auth bypass exposes all user notes 5.3 0.3% open-webui Jun 17 MEDI CVE-2026-54021 open-webui: auth bypass reaches restricted Ollama backends 6.3 0.2% open-webui Jun 17 MEDI E CVE-2026-54019 open-webui: RAG ACL bypass exposes private KB chunks 6.5 0.3% open-webui Jun 17 MEDI E CVE-2026-54016 Open WebUI: BOLA exposes private knowledge base files 4.3 0.3% open-webui Jun 17 MEDI E CVE-2026-54015 Open WebUI: IDOR exposes private prompt history 6.4 0.2% open-webui Jun 17 MEDI E CVE-2026-54014 open-webui: path traversal exposes sibling dirs 4.3 0.3% open-webui Jun 17 MEDI E CVE-2026-54009 open-webui: cross-user file read via auth bypass 6.5 0.3% open-webui Jun 17 MEDI E CVE-2026-54006 open-webui: auth bypass allows cross-user calendar injection 4.3 0.2% open-webui Jun 17 MEDI CVE-2026-54233 vLLM: decompression bomb OOM via audio endpoint 6.5 0.4% vllm Jun 17 MEDI E CVE-2026-54236 vLLM: heap address leak enables ASLR bypass 5.3 0.8% vllm Jun 17 MEDI GHSA-8jr5-v98p-w75m vllm: EXIF/tRNS preprocessing gap enables adversarial input 4.8 — vllm Jun 17 MEDI CVE-2026-54235 vLLM: NaN/Inf bypass crashes GPU inference workers 6.5 0.3% vllm Jun 17 MEDI GHSA-664h-gpgq-h6xx n8n: viewer role can start/cancel/delete eval workflow runs 5.4 — n8n Jun 17 MEDI CVE-2026-12491 vLLM: image metadata mishandling corrupts multimodal inputs 4.8 0.2% rhaiis/vllm-cpu-rhel9 Jun 17 MEDI CVE-2026-54314 n8n: decompression bomb DoS via public webhook — 0.4% n8n Jun 16 MEDI CVE-2026-48782 pydantic-ai: SSRF IPv6 bypass exposes cloud IAM creds 6.8 0.3% pydantic-ai Jun 16 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