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 4307 resultsAMP for WP: arbitrary shortcode execution by auth users
CVE-2026-103908JetBrains Datalore: IDOR exposes other workspaces' notebooks
CVE-2026-123291JetBrains Datalore: hidden notebook code exposed unauthenticated
CVE-2026-123290JetBrains Datalore: improper authorization lets viewers edit files
CVE-2026-123289JetBrains Datalore: stored XSS in notebook charts
CVE-2026-123288JetBrains Datalore: unauthenticated download of private notebooks
CVE-2026-123287JetBrains Datalore: improper authz exposes storage token
CVE-2026-123286JetBrains Datalore: argument injection allows sidecar command execution
CVE-2026-123281JetBrains Datalore: view-only users can run notebook code
CVE-2026-123279AG2: shell filter bypass via newline enables RCE
CVE-2026-113663Codex Desktop Windows: argument injection runs code
CVE-2026-110930ESPectre: unsafe NPZ pickle load allows code execution
CVE-2026-102739stable-diffusion.cpp: OOB read via crafted safetensors
CVE-2026-70660H2O: access-log buffer overflow crashes HTTP server
CVE-2026-55368H2O: unbounded CONNECT-UDP capsule buffering causes DoS
CVE-2026-55367npcpy: improper input validation in MLX provider
CVE-2026-122015Mistral Vibe: RCE via repo-configured gpg.program
CVE-2026-122135Mistral Vibe: Git filter RCE on repo open
CVE-2026-122134Mistral Vibe: untrusted git.exe path allows RCE on Windows
CVE-2026-122133SQL::Abstract::Tree: XSS via unescaped html profile output
CVE-2026-121008Frequently 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