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 2345 results — no patch CVE-2026-86099 Chainlit: path traversal via sessionId wipes directories 8.2 0.4% chainlit Sep 9 MEDI E CVE-2026-87820 CyberPanel: AI Scanner endpoints leak admin usernames unauthenticated 5.3 0.5% — Sep 9 HIGH E CVE-2026-87811 SiYuan: stored XSS in notebook template paths 7.3 0.2% — Sep 9 HIGH CVE-2026-83593 WPBot: unauth stored XSS in chatbot conversation field 7.2 0.3% WPBot – AI ChatBot for Live Support, Lead Generation, AI Services Sep 9 HIGH CVE-2026-12855 InsydeH2O: BIOS memory corruption enables local RCE 8.2 0.1% InsydeH2O Sep 9 HIGH CVE-2026-6485 InsydeH2O UEFI: BIOS Shell allows Secure Boot bypass 8.2 0.1% InsydeH2O Sep 9 MEDI CVE-2026-85981 Auth0 AD/LDAP Connector: unauth local panel leaks AD creds 6.7 0.1% — Sep 8 UNKN E CVE-2026-79721 MLflow: malicious model artifact enables RCE on load — 0.3% mlflow Sep 8 HIGH CVE-2026-86730 Craft CMS: authenticated RCE via Yii2 behavior injection 8.8 0.4% — Sep 8 UNKN CVE-2026-82584 Igniter: ANSI escapes forge mix install trust prompt — 0.3% — Sep 7 MEDI E CVE-2026-86289 Ollama: integer overflow in GGUF decoder causes DoS 4.3 0.4% ollama Sep 7 MEDI CVE-2026-86332 RHOAI dashboard: broken authz leaks NIM/NGC secrets 6.5 0.2% rhoai/odh-mod-arch-mlflow-rhel9 Sep 7 MEDI CVE-2026-86258 nbviewer: path traversal leaks notebooks/credentials 5.9 0.4% — Sep 6 HIGH E CVE-2026-86177 Pterodactyl Panel: subuser escalation to console RCE 8.8 0.3% — Sep 5 MEDI CVE-2026-17631 Langflow: authenticated SSRF exposes internal hosts 6.5 0.2% langflow Sep 4 HIGH CVE-2026-17627 Langflow: IDOR leaks and poisons workflow history 7.1 0.2% langflow Sep 4 MEDI CVE-2026-17622 Langflow: path traversal exposes sensitive files 6.5 0.5% langflow Sep 4 MEDI CVE-2026-17621 Langflow: path traversal allows arbitrary file read 5.4 0.3% langflow Sep 4 MEDI CVE-2026-14470 Langflow: auth'd path traversal reads arbitrary files 6.5 0.3% langflow Sep 4 HIGH CVE-2026-19306 Langflow: chat attachment path traversal leaks server secrets 7.7 0.4% langflow Sep 4 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