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-2026-56348n8n: SSRF bypasses allowlist, exfiltrates credentials9.10.5%n8nJun 22CRITCVE-2026-10561Langflow: auth bypass + unauthenticated RCE (CVSS 10)10.00.8%langflowJun 22CRITCVE-2026-7664Langflow: auth bypass in MCP endpoint, CVSS 9.89.80.5%Langflow OSSJun 22CRITCVE-2024-58351Flowise: RCE and sandbox escape via overrideConfig9.80.7%FlowiseJun 20CRITECVE-2026-55447Langflow: TAR symlink traversal enables full RCE9.60.7%langflowJun 19CRITCVE-2026-55255Langflow: IDOR allows cross-user flow execution9.90.9%langflowJun 19CRITECVE-2026-54527jupyterlab-git: stored XSS escalates to full RCE9.00.5%@jupyterlab/gitJun 19CRITCVE-2026-12048pgAdmin 4: Stored XSS enables full browser session hijack9.30.3%—Jun 18CRITCVE-2026-44727jupyter-server: stored XSS yields kernel RCE9.00.4%notebookJun 18CRITGHSA-cwj8-7gp2-ggcwpraisonai-platform: hardcoded JWT secret enables full auth bypass9.8—praisonai-platformJun 18CRITGHSA-f38v-77qj-h4jqpraisonai-platform: hardcoded JWT secret enables full auth bypass9.8—praisonai-platformJun 18CRITGHSA-29w3-p9w9-wc47PraisonAI: multiedit path traversal, arbitrary file R/W9.1—praisonaiJun 18CRITGHSA-j4f3-55x4-r6q2praisonai: MCP HTTP server unauthenticated tool invocation9.8—praisonaiJun 18CRITGHSA-9752-mhqh-h34fpraisonai npm: AgentOS missing auth enables agent abuse9.4—praisonaiJun 18CRITGHSA-p69m-4f92-2v84praisonai: sandbox escape in codeMode → full host RCE9.8—praisonaiJun 18CRITGHSA-vmmj-pfw7-fjwppraisonai: sandbox escape gives RCE via codeMode tool9.9—praisonaiJun 18CRITGHSA-p75f-6fp4-p57wPraisonAI: unauthenticated RCE via MCP connect endpoint9.8—praisonaiJun 18CRITGHSA-892r-p3jq-jp24PraisonAI AgentOS: unauth remote agent invocation (CVSS 9.8)9.8—praisonaiJun 18CRITGHSA-x8cv-xmq7-p8xppraisonaiagents: unauth AgentTeam API allows agent takeover9.8—praisonaiagentsJun 18CRITGHSA-fq2m-6wqh-x44gpraisonai: unauthenticated Jobs API enables remote agent RCE9.8—praisonaiJun 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