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 533 results — Critical severityCVE-2026-61732Decepticon: ChatML token injection yields sandbox RCE10.01.5%decepticon-sdkSep 24CRITCVE-2026-77987GitHub Enterprise Server: SSRF to RCE in notebook viewer9.80.9%—Sep 22CRITECVE-2026-77254MCP Atlassian: missing auth exposes Jira/Confluence9.10.6%mcp-atlassianSep 22CRITCVE-2026-77244MCP Atlassian: unauthenticated access to operator Jira/Confluence10.00.3%mcp-atlassianSep 22CRITCVE-2026-94127F5 BIG-IP APM: unauthenticated RCE via OAuth server9.826.6%—Sep 22CRITECVE-2026-46649Joplin Server: SSO code brute force yields session takeover—0.5%—Sep 21CRITCVE-2025-66455LMDeploy: pickle deserialization RCE in DistServe9.81.3%lmdeploySep 18CRITECVE-2025-59953LMDeploy: unsafe pickle deserialization allows RCE9.80.9%lmdeploySep 16CRITECVE-2026-57148PraisonAI: hardcoded JWT secret enables auth bypass9.80.6%praisonaiSep 15CRITECVE-2026-57147PraisonAI: hardcoded JWT secret allows auth bypass9.80.8%praisonaiSep 15CRITECVE-2026-57141PraisonAI: codeMode sandbox escape allows unauthenticated RCE9.80.7%praisonaiSep 15CRITECVE-2026-57140PraisonAI: unauthenticated AgentOS API exposes agents9.40.6%praisonaiSep 15CRITECVE-2026-57139PraisonAI: unauthenticated MCP server exposes agent tools9.80.8%praisonaiSep 15CRITECVE-2026-57138PraisonAI: codeMode sandbox escape allows RCE9.90.7%praisonaiSep 15CRITCVE-2026-12944Langflow: SSRF-driven root RCE via component imports9.60.4%langflowSep 14CRITCVE-2026-57145PraisonAI: path traversal lets agents read/write any file9.10.5%praisonaiSep 14CRITECVE-2026-57131PraisonAI: no-auth API exposes agent execution9.81.0%praisonaiSep 14CRITECVE-2026-57127PraisonAI: auth middleware fails open, exposes agents9.80.9%praisonaiSep 14CRITECVE-2026-57124PraisonAI: unauth RCE via MCP connect endpoint9.81.0%praisonaiSep 14CRITECVE-2026-57125PraisonAI: unauth RCE via YAML approval bypass9.80.6%praisonaiSep 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