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 2876 results — no patchCVE-2026-57133PraisonAI: allowlist bypass in shell() enables RCE8.80.8%praisonaiSep 15HIGHECVE-2026-57112PraisonAI: DNS rebinding exposes MCP SSE tool calls8.30.2%praisonaiagentsSep 15MEDIECVE-2026-90878vLLM: chat_template abuse causes resource exhaustion4.30.5%vllmSep 15HIGHCVE-2026-91771wandb: path traversal enables arbitrary file write8.81.2%wandbSep 15HIGHECVE-2026-79411Bagisto: privilege escalation to full admin via role change8.80.5%—Sep 15MEDICVE-2026-18117Concrete CMS: stored XSS in alias name enables privilege escalation5.40.1%—Sep 14CRITCVE-2026-12944Langflow: SSRF-driven root RCE via component imports9.60.4%langflowSep 14MEDIECVE-2026-90818LobsterAI: SSRF in browser network config sync4.30.5%—Sep 14HIGHCVE-2026-81902Concrete CMS: CSRF in removeOrphanedBlocks deletes page content8.10.2%—Sep 14MEDICVE-2026-7884IBM Cognos Analytics: stored XSS via profile name fields5.40.2%—Sep 14MEDICVE-2026-12767Langflow: unauthenticated SSRF enables internal probing6.50.3%langflowSep 14MEDICVE-2026-12766Langflow: SSRF allows internal network probing5.40.2%langflowSep 14MEDICVE-2026-12765Langflow: unauthenticated SSRF enables internal network probing6.50.3%langflowSep 14MEDICVE-2026-12763Langflow: MCP cache isolation flaw leaks user context4.20.2%langflowSep 14MEDIECVE-2026-55093tract-nnef: integer overflow enables heap OOB read, crash6.10.2%—Sep 14MEDICVE-2026-17628Langflow: improper auth allows account password change5.40.4%langflowSep 14MEDIECVE-2026-73497MCP Atlassian: DNS rebinding SSRF reaches cloud metadata6.50.4%mcp-atlassianSep 14HIGHECVE-2026-73496MCP Atlassian: path traversal enables server file disclosure7.70.5%mcp-atlassianSep 14HIGHCVE-2026-50270dd-trace-java: baggage header parsing causes DoS7.50.8%—Sep 14HIGHCVE-2026-90943Filament Comments: stored XSS via admin panel8.70.4%—Sep 14Frequently 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