AI Threat Alert
AI 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 1382 results — Active exploitation CVE-2025-71343 picklescan: scanner bypass lets malicious pickle files evade detection 8.1 0.3% picklescan Jul 4 HIGH E CVE-2025-71342 picklescan: idlelib bypass hides pickle RCE 8.1 0.4% picklescan Jul 4 CRIT E CVE-2026-12481 Keras: safe_mode=None bypass enables Lambda RCE 9.8 0.5% keras Jul 3 HIGH E CVE-2026-50181 Langroid: path traversal escapes sandboxed file tools 7.1 0.2% langroid Jul 2 MEDI E CVE-2026-58653 PraisonAI: IDOR cross-tenant data pollution 4.3 0.2% praisonai Jul 2 UNKN E CVE-2026-8147 MLflow: auth bypass allows cross-experiment trace access — 0.4% mlflow/mlflow Jul 2 HIGH E CVE-2026-49119 Gradio: path traversal in FileExplorer leaks files 7.5 0.7% gradio Jul 1 HIGH E CVE-2026-57516 Ray: RCE via pickle/torch deserialization in WebDataset 8.8 0.6% ray Jul 1 MEDI E CVE-2026-12480 Keras: incomplete fix reopens HDF5 arbitrary file read 5.5 0.1% keras Jul 1 UNKN E CVE-2026-8387 ClearML: path traversal in zip extraction enables RCE — 0.4% allegroai/clearml Jul 1 HIGH E CVE-2025-71374 picklescan: scanner bypass enables pickle RCE 8.1 0.6% picklescan Jun 30 HIGH E CVE-2025-71371 picklescan: malicious pickle bypasses RCE scan 8.1 0.5% picklescan Jun 30 HIGH E CVE-2025-71368 picklescan: scan bypass lets malicious pickles hit RCE 8.1 0.8% picklescan Jun 30 HIGH E CVE-2025-71363 picklescan: scanner bypass enables pickle RCE 8.1 0.6% picklescan Jun 30 UNKN E CVE-2025-71355 Picklescan: NumPy gadget bypass enables pickle RCE — 0.6% picklescan Jun 30 HIGH E CVE-2025-71352 picklescan: RCE bypass via trace.Trace.runctx 8.1 0.6% picklescan Jun 30 HIGH E CVE-2025-71350 picklescan: scanner bypass enables pickle RCE 8.1 0.4% torch Jun 30 HIGH E CVE-2025-71349 picklescan: bypass allows undetected pickle RCE 8.1 0.6% picklescan Jun 30 MEDI E CVE-2026-56399 Open WebUI: SSRF in web retrieval hits internal services 5.0 0.3% open-webui Jun 30 CRIT E CVE-2026-7663 Langflow: auth bypass in MCP transport exposes projects 9.8 0.3% langflow Jun 30 Frequently 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