AI Threat AlertAI 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 1431 results — has patchGHSA-2rcg-mm5h-xchxpraisonaiagents: @file: path traversal reads arbitrary files7.5—praisonaiagentsJun 18CRITGHSA-j4hj-7hfh-g2f4praisonai: silent auth bypass exposes agent exec endpoints9.8—praisonaiJun 18HIGHGHSA-vxgj-xg5c-p4h7praisonaiagents: SSRF DNS bypass exposes internal services8.5—praisonaiagentsJun 18CRITGHSA-4869-x4pr-q22xPraisonAI: Unauthenticated RCE via Jobs API auth bypass9.8—praisonaiagentsJun 18HIGHGHSA-p4pj-vh7h-6cqhpraisonai: unauthenticated path traversal leaks server files7.5—praisonaiJun 18CRITGHSA-x227-pf99-vffgpraisonaiagents: unauthenticated MCP SSE server enables RCE9.8—praisonaiagentsJun 18MEDIGHSA-pv2j-rghr-v5r9praisonaiagents: sandbox escape via format-spec read6.5—praisonaiagentsJun 18MEDIGHSA-6h9p-93hq-q7h6praisonaiagents: SSRF bypass via SpiderTools redirect6.5—praisonaiagentsJun 18HIGHGHSA-w6h2-fr4q-xvxvPraisonAI: file tool shell injection enables RCE8.8—praisonaiJun 18HIGHGHSA-v847-hxxw-3pxgPraisonAI: streaming bypass enables dangerous tool execution7.8—praisonaiJun 18HIGHGHSA-63v4-w882-g4x2PraisonAI: XSS bypasses human-in-the-loop tool approval8.8—praisonaiJun 18HIGHGHSA-fc26-m9pf-v56qPraisonAI LinearBot: webhook auth bypass enables agent exec8.6—praisonaiJun 18HIGHGHSA-j7qx-p75m-wp7gPraisonAI: path traversal exposes arbitrary host files7.5—praisonaiJun 18HIGHGHSA-qvpf-j64c-jmhrPraisonAI: auth bypass via Slack app_mention handler8.3—praisonaiJun 18HIGHGHSA-5qw8-f2g9-ff29PraisonAI: auth bypass exposes recipe API to unauthenticated callers8.2—praisonaiJun 18HIGHGHSA-vmf9-xx9w-86wxPraisonAI: DNS rebinding exposes MCP agent tools8.3—praisonaiJun 18HIGHGHSA-22cj-m4wf-fv2cPraisonAI: path traversal in agent tools exposes credentials7.5—praisonaiJun 18HIGHGHSA-8579-rgg5-ph2mpraisonai: Discord approval bypass executes agent tools8.8—praisonaiJun 18MEDIGHSA-35w5-pcw4-jx94praisonaiagents: unauth SSE endpoint enables event injection4.3—praisonaiagentsJun 18MEDICVE-2026-54386marimo: reflected XSS enables JS injection in notebooks6.10.2%marimoJun 17Frequently 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