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 667 results — High severity, no patch CVE-2026-54320 Daytona: email bypass grants unauthorized org Owner access 8.4 — — Jun 23 HIGH CVE-2025-71376 picklescan: scanner bypass enables undetected RCE 8.1 — picklescan Jun 23 HIGH CVE-2025-71370 picklescan: scanner bypass enables arbitrary code execution 8.1 — picklescan Jun 23 HIGH CVE-2025-71365 picklescan: detection bypass enables RCE via numpy.f2py 8.1 — picklescan Jun 23 HIGH CVE-2025-71341 picklescan: scanner bypass enables undetected RCE via pickle 8.1 — picklescan Jun 23 HIGH CVE-2025-71337 Flowise: account takeover via unverified email change 8.3 — Flowise Jun 23 HIGH CVE-2026-54232 vLLM: dependency confusion RCE backdoors container images 8.8 — vllm Jun 22 HIGH CVE-2026-50132 Budibase: account hijack via chat identity CSRF 7.3 0.0% — Jun 22 HIGH CVE-2025-71358 picklescan: scanner bypass enables RCE via pickle 8.1 — picklescan Jun 22 HIGH CVE-2025-71344 picklescan: scanner bypass enables undetected pickle RCE 8.1 — picklescan Jun 22 HIGH CVE-2025-71339 picklescan: scanner bypass enables arbitrary code execution 8.1 — picklescan Jun 22 HIGH CVE-2026-55409 Filament: stored XSS in disabled RichEditor field 7.6 — — Jun 22 HIGH CVE-2026-48505 Filament: MFA race condition enables recovery code reuse 7.4 — — Jun 22 HIGH CVE-2026-56268 Flowise: cross-workspace chatflow config disclosure 7.7 — Flowise Jun 22 HIGH CVE-2026-10845 WebSphere AS: JAX-WS auth bypass, unauthorized access 7.3 — — Jun 22 HIGH CVE-2026-56104 Chainlit: session hijacking via WebSocket restoration 8.2 — chainlit Jun 22 HIGH CVE-2026-9029 Grafana: stored XSS in geomap bypasses CVE-2023-0507 fix 7.3 — — Jun 22 HIGH E CVE-2025-71378 picklescan: detection bypass enables RCE via pickle files 8.1 — picklescan Jun 21 HIGH E CVE-2025-71357 picklescan: detection bypass enables RCE via malicious models 8.1 — picklescan Jun 21 HIGH E CVE-2025-71351 picklescan: scanner bypass enables RCE via pickle files — — picklescan Jun 21 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