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 2349 results — no patch CVE-2026-56211 libaom: AV1 SVC OOB write enables RCE 7.1 0.5% rhaiis/vllm-cpu-rhel9 Jun 19 HIGH CVE-2026-56210 libaom: AV1 SVC bounds-check miss leaks heap, crashes 7.1 0.3% rhaiis/vllm-cpu-rhel9 Jun 19 HIGH CVE-2026-56208 libaom: heap overflow in AV1 encoder LAP mode 7.6 0.4% rhaiis/vllm-cpu-rhel9 Jun 19 HIGH CVE-2026-56209 libaom: arbitrary address write in AV1 SVC codec 7.1 0.4% rhaiis/vllm-cpu-rhel9 Jun 19 HIGH GHSA-vcv2-r9jh-99m5 agentic-flow: MCP tool args enable OS command injection RCE 8.8 — — Jun 19 MEDI CVE-2026-12706 FFmpeg RASC: UAF in decoder crashes AI inference containers 6.5 0.2% rhoai/odh-vllm-gaudi-rhel9 Jun 19 CRIT CVE-2026-12048 pgAdmin 4: Stored XSS enables full browser session hijack 9.3 0.3% — Jun 18 HIGH E CVE-2026-56078 PraisonAI: path traversal → arbitrary file read/write/RCE 8.8 0.9% PraisonAI Jun 18 MEDI E CVE-2026-56077 PraisonAI: agent ID collision leaks system prompts 6.5 0.4% PraisonAI Jun 18 HIGH E CVE-2026-56076 PraisonAI: CORS bypass enables arbitrary agent execution 8.1 0.7% PraisonAI Jun 18 HIGH E CVE-2026-56075 PraisonAI: RCE via hardcoded approval_mode bypass 8.8 0.7% PraisonAI Jun 18 MEDI E CVE-2026-56074 PraisonAI: tool approval bypass enables credential theft 5.5 0.2% PraisonAI Jun 18 CRIT CVE-2026-44727 jupyter-server: stored XSS yields kernel RCE 9.0 0.4% notebook Jun 18 HIGH GHSA-6jcq-6546-qrrw PraisonAI: sandbox escape via silent Landlock fallback 8.8 — praisonaiagents Jun 18 HIGH GHSA-7qw2-w5rc-37x2 PraisonAI: workflow policy bypass enables shell RCE 7.8 — praisonaiagents Jun 18 UNKN E CVE-2026-53875 picklescan: scanner bypass enables PyTorch RCE — 0.4% picklescan Jun 17 CRIT E CVE-2026-53874 picklescan: scanner bypass enables pickle RCE 9.8 0.5% picklescan Jun 17 CRIT E CVE-2026-53873 picklescan: blocklist bypass allows arbitrary code exec 9.8 0.5% picklescan Jun 17 HIGH E CVE-2026-53872 picklescan: arbitrary file read bypasses RCE blocklist 7.5 0.5% picklescan Jun 17 CRIT E CVE-2026-3490 picklescan: blocklist bypass enables full RCE 10.0 0.6% picklescan Jun 17 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