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 1527 results — Medium severityCVE-2026-77252MCP Atlassian: filter bypass exposes Jira/Confluence data6.50.3%mcp-atlassianSep 22MEDIECVE-2026-77250MCP Atlassian: cleartext OAuth token file readable locally6.10.1%mcp-atlassianSep 22MEDIECVE-2026-77265MCP Atlassian: DNS-rebinding SSRF exposes internal services5.90.3%mcp-atlassianSep 22MEDIECVE-2026-77270MCP Atlassian: path traversal in attachment upload leaks files6.50.5%mcp-atlassianSep 22MEDIECVE-2026-85709LightRAG: error messages leak paths and DB credentials5.30.4%lightrag-hkuSep 22MEDICVE-2026-93344MarketKing WP: missing authz exposes vendor financial pages6.50.4%—Sep 22MEDICVE-2026-79315x-ui: reflected XSS in admin panel menu highlighting4.70.3%—Sep 22MEDIECVE-2026-61612CKAN MCP Server: DNS-based SSRF reaches cloud metadata5.70.4%—Sep 22MEDICVE-2025-14486PixelPlay WP: missing auth lets attackers delete API keys5.30.3%—Sep 22MEDICVE-2026-94625vLLM: Mooncake placeholder leak enables slow DoS5.30.5%vllmSep 21MEDIECVE-2026-59815Joplin Server: pending share invite allows item injection4.30.2%—Sep 21MEDIECVE-2026-46650Joplin: XSS via unanchored URL regex in shared notes4.40.3%—Sep 21MEDIECVE-2026-59816Joplin Server: path traversal in transcribe API leaks data4.30.4%—Sep 21MEDIECVE-2026-55179Joplin Server: IDOR exposes other users' note content6.50.3%—Sep 21MEDIECVE-2026-94387Aureus ERP: stored XSS in Chatter change log5.40.3%—Sep 21MEDIECVE-2026-94094OpenClaw: unbounded file read enables canvas host DoS4.30.5%openclawSep 20MEDICVE-2026-93989vLLM: bad_words OOB index corrupts cross-request logits4.30.2%vllmSep 19MEDICVE-2026-93841vLLM: OOB write in penalty kernel corrupts requests5.30.2%vllmSep 18MEDICVE-2026-93840vLLM: token ID validation flaw corrupts cross-request logits5.30.2%vllmSep 18MEDICVE-2026-89278GPTranslate WP: plaintext AI API key exposed to anyone5.30.4%—Sep 18Frequently 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