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 2346 results — no patch CVE-2026-40257 OP-TEE: off-by-one in SHA-3 CE overflows TEE kernel heap 5.5 0.2% — Jul 6 MEDI CVE-2026-59152 LangSmith SDK: arbitrary file read via TracingMiddleware 5.0 0.2% langsmith-sdk Jul 6 LOW E CVE-2026-14742 LangGraph: weak hash in task cache risks poisoning 3.1 0.2% langgraph Jul 5 LOW E CVE-2026-14738 exo: weak hash algorithm in vision feature cache key 3.7 0.3% — Jul 5 MEDI E CVE-2026-14647 ONNX: OOB read in shape inference parsing untrusted models 4.3 0.4% onnx Jul 4 CRIT E CVE-2026-14535 fickling: shared-state bug disables ML pickle allowlist check 9.8 0.6% fickling Jul 4 HIGH E CVE-2026-14534 fickling: denylist gaps let malicious pickles execute 8.8 0.6% fickling Jul 4 LOW E CVE-2026-14630 AI-fundermentals: weak hash exposes chat session data 3.1 0.2% — Jul 4 HIGH E CVE-2026-12196 HestiaCP: cronjob flaw lets low-priv users get root — 0.4% — Jul 4 HIGH CVE-2025-71380 n8n: authenticated RCE via Execute Command node 8.8 0.6% n8n Jul 4 HIGH E CVE-2025-71375 picklescan: detection bypass enables pickle RCE 8.1 0.5% picklescan Jul 4 HIGH E CVE-2025-71373 picklescan: methodcaller bypass enables pickle RCE 8.1 0.6% picklescan Jul 4 HIGH E CVE-2025-71372 Picklescan: RCE gadget bypasses pickle safety scanner 8.1 0.5% picklescan Jul 4 HIGH E CVE-2025-71369 picklescan misses malicious pickles via torch decoder 8.1 0.6% picklescan Jul 4 HIGH E CVE-2025-71367 picklescan: attrgetter bypass evades malicious pickle scan 8.1 0.6% picklescan Jul 4 HIGH E CVE-2025-71366 picklescan: scan bypass lets malicious pickle RCE 8.1 0.6% picklescan Jul 4 HIGH E CVE-2025-71364 picklescan: scanner blind spot enables pickle RCE 8.1 0.8% picklescan Jul 4 HIGH E CVE-2025-71362 picklescan: scanner bypass enables RCE via numpy eval 8.1 0.4% picklescan Jul 4 HIGH E CVE-2025-71360 picklescan: scanner bypass enables pickle RCE 8.1 0.4% picklescan Jul 4 HIGH E CVE-2025-71359 picklescan: scan bypass lets malicious models RCE 8.1 0.6% picklescan Jul 4 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