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 1026 results — High severity CVE-2026-56351 n8n: SQL injection in DB nodes via identifier values 8.2 — n8n Jun 24 HIGH CVE-2026-56270 Flowise: auth bypass exposes OAuth secrets in cleartext 7.5 — Flowise Jun 24 HIGH CVE-2025-71361 picklescan: scanner bypass allows RCE via pickle load 8.1 — picklescan Jun 24 HIGH CVE-2025-71354 picklescan: scanner bypass enables arbitrary code execution 8.1 — picklescan Jun 24 HIGH CVE-2026-7574 Claude Desktop: VM integrity bypass enables RCE 8.7 0.1% Claude Desktop Cowork Jun 23 HIGH CVE-2026-54320 Daytona: email bypass grants unauthorized org Owner access 8.4 0.2% — Jun 23 HIGH CVE-2026-52812 Gogs LFS: cross-tenant object disclosure via dedupe bypass — — gogs.io/gogs Jun 23 HIGH CVE-2025-71376 picklescan: scanner bypass enables undetected RCE 8.1 0.3% picklescan Jun 23 HIGH CVE-2025-71370 picklescan: scanner bypass enables arbitrary code execution 8.1 0.4% picklescan Jun 23 HIGH CVE-2025-71365 picklescan: detection bypass enables RCE via numpy.f2py 8.1 0.3% picklescan Jun 23 HIGH CVE-2025-71341 picklescan: scanner bypass enables undetected RCE via pickle 8.1 0.5% picklescan Jun 23 HIGH CVE-2025-71337 Flowise: account takeover via unverified email change 8.3 0.3% Flowise Jun 23 HIGH CVE-2026-52798 Gogs: Stored XSS via .ipynb Markdown re-render bypass 8.9 — gogs.io/gogs Jun 22 HIGH CVE-2026-54353 Budibase: SSRF via DNS rebinding in automation steps 8.5 — @budibase/backend-core Jun 22 HIGH CVE-2026-54232 vLLM: dependency confusion RCE backdoors container images 8.8 0.3% 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 0.2% picklescan Jun 22 HIGH CVE-2025-71344 picklescan: scanner bypass enables undetected pickle RCE 8.1 0.4% picklescan Jun 22 HIGH CVE-2025-71339 picklescan: scanner bypass enables arbitrary code execution 8.1 0.3% picklescan Jun 22 HIGH CVE-2026-55409 Filament: stored XSS in disabled RichEditor field 7.6 0.2% — Jun 22 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