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 1961 results — Active exploitationCVE-2026-58653PraisonAI: IDOR cross-tenant data pollution4.30.3%praisonaiJul 2HIGHECVE-2026-8147MLflow: auth bypass allows cross-experiment trace access8.10.5%mlflow/mlflowJul 2HIGHECVE-2026-49119Gradio: path traversal in FileExplorer leaks files7.50.7%gradioJul 1HIGHECVE-2026-49857auth-fetch-mcp: SSRF bypass via IPv6 loopback7.40.5%auth-fetch-mcpJul 1HIGHECVE-2026-57516Ray: RCE via pickle/torch deserialization in WebDataset8.80.9%rayJul 1MEDIECVE-2026-12480Keras: incomplete fix reopens HDF5 arbitrary file read5.50.2%kerasJul 1UNKNECVE-2026-8387ClearML: path traversal in zip extraction enables RCE—0.4%allegroai/clearmlJul 1HIGHECVE-2025-71374picklescan: scanner bypass enables pickle RCE8.10.7%picklescanJun 30HIGHECVE-2025-71371picklescan: malicious pickle bypasses RCE scan8.10.6%picklescanJun 30HIGHECVE-2025-71368picklescan: scan bypass lets malicious pickles hit RCE8.10.8%picklescanJun 30HIGHECVE-2025-71363picklescan: scanner bypass enables pickle RCE8.10.7%picklescanJun 30UNKNECVE-2025-71355Picklescan: NumPy gadget bypass enables pickle RCE—0.6%picklescanJun 30HIGHECVE-2025-71352picklescan: RCE bypass via trace.Trace.runctx8.10.7%picklescanJun 30HIGHECVE-2025-71350picklescan: scanner bypass enables pickle RCE8.10.4%torchJun 30HIGHECVE-2025-71349picklescan: bypass allows undetected pickle RCE8.10.6%picklescanJun 30MEDIECVE-2026-56399Open WebUI: SSRF in web retrieval hits internal services5.00.5%open-webuiJun 30CRITECVE-2026-7873Langflow: authenticated RCE enables credential theft9.96.2%langflowJun 30CRITECVE-2026-7663Langflow: auth bypass in MCP transport exposes projects9.80.5%langflowJun 30CRITECVE-2026-10560Langflow: missing auth on build API leaks data, enables DoS9.10.5%langflowJun 30CRITECVE-2026-10134Langflow: unauthenticated RCE via tool_code injection10.02.3%langflowJun 30Frequently 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