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 1321 results — High severity CVE-2026-44436 Quicly: QUIC DoS via oversized Connection ID overflow 7.5 0.3% — Jul 16 HIGH CVE-2026-44435 H2O/Quicly: unauthenticated QUIC DoS via assertion crash 7.5 0.3% — Jul 16 HIGH CVE-2026-44433 Quicly/H2O: QUIC flow-control bug enables memory exhaustion DoS 7.5 0.3% — Jul 16 HIGH E CVE-2026-63086 TGI: SSRF via image_url exposes cloud metadata creds 8.6 0.3% text-generation-inference Jul 16 HIGH CVE-2026-23538 Feast: unauth WebSocket connections cause DoS 7.5 0.7% rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel9 Jul 16 HIGH CVE-2026-54449 LangBot: RCE via arbitrary STDIO MCP command 8.8 — langbot Jul 15 HIGH E CVE-2026-61446 PraisonAI: RCE via unsigned plugin auto-load 8.4 0.2% PraisonAI Jul 15 HIGH E CVE-2026-61443 PraisonAI: path traversal leads to RCE via SkillTools 8.1 0.5% PraisonAI Jul 15 HIGH E CVE-2026-61438 PraisonAI: RCE via broken AST sandbox in workflows 7.3 0.2% PraisonAI Jul 15 HIGH E CVE-2026-61436 PraisonAI: missing webhook signature check spoofs agents 8.6 0.3% PraisonAI Jul 15 HIGH E CVE-2026-61435 PraisonAI: Host header spoof bypasses agent auth 8.2 0.4% PraisonAI Jul 15 HIGH E CVE-2026-61433 PraisonAI: code injection via unsafe config codegen 7.8 0.1% PraisonAI Jul 15 HIGH E CVE-2026-61430 PraisonAI: DNS rebinding SSRF bypass in web_crawl 8.5 0.2% PraisonAI Jul 15 HIGH E CVE-2026-61427 PraisonAI: MCP server auth bypass by default 7.3 0.3% PraisonAI Jul 15 HIGH CVE-2026-60085 PraisonAI: sandbox policy no-op enables RCE, file read 7.5 0.2% PraisonAI Jul 15 HIGH E CVE-2026-56400 Open WebUI: CORS misconfig + CSRF enables admin RCE 8.3 0.3% open-webui Jul 15 HIGH CVE-2026-56398 Open WebUI: OAuth avatar stored XSS risks account takeover 7.3 0.4% open-webui Jul 15 HIGH CVE-2026-50158 yutu: arbitrary file write via MCP caption-download tool 7.7 — github.com/eat-pray-ai/yutu Jul 14 HIGH E CVE-2026-62240 CrewAI: SSRF filter bypass via DNS rebinding 7.4 0.3% crewai Jul 13 HIGH CVE-2026-62200 OpenClaw: Git ext transport flaw allows auth-bypass RCE 8.8 0.3% openclaw Jul 13 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