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 1527 results — Medium severityCVE-2026-9149libsolv: heap overflow via crafted .solv file causes DoS6.5—rhoai/odh-mlflow-operator-rhel9May 20MEDICVE-2026-9150libsolv: stack overflow in Debian parser causes DoS6.5—rhoai/odh-mlflow-operator-rhel9May 20MEDIGHSA-c2c9-mfw7-p8hwFlowise: cross-workspace chatflow config disclosure——flowiseMay 20MEDIGHSA-59fh-9f3p-7m39Flowise: mass assignment bypasses password controls——flowiseMay 20MEDIGHSA-m837-xvxr-vqwgFlowise: hardcoded CORS wildcard enables drive-by credential abuse——flowiseMay 20MEDIGHSA-2vx9-7wpg-88jqn8n: path traversal bypasses file access restriction6.4—n8nMay 19MEDICVE-2026-45582n8n-mcp: telemetry leak exposes workflow URL secrets6.50.3%n8n-mcpMay 18MEDIECVE-2026-45667open-webui: unauth endpoint drains embedding budget/DoS6.50.3%open-webuiMay 14MEDIECVE-2026-45666open-webui: IDOR exposes cross-user note data6.50.3%open-webuiMay 14MEDIECVE-2026-45397Open WebUI: unauthenticated RAG config leaks AI pipeline5.30.8%open-webuiMay 14MEDIECVE-2026-45396open-webui: mass assignment enables leaderboard poisoning5.40.3%open-webuiMay 14MEDIECVE-2026-45387open-webui: system prompt leakage via model read API4.30.2%open-webuiMay 14MEDIECVE-2026-45386open-webui: auth bypass lets read-only users pin messages4.30.3%open-webuiMay 14MEDIECVE-2026-45385Open WebUI: IDOR lets members tamper with admin messages4.30.3%open-webuiMay 14MEDIECVE-2026-45365open-webui: auth bypass exposes admin-restricted models5.40.2%open-webuiMay 14MEDIECVE-2026-45351Open WebUI: admin system prompts exposed to all users6.50.3%open-webuiMay 14MEDIECVE-2026-45347Open WebUI: blind SSRF via PDF export HTML injection4.30.2%open-webuiMay 14MEDIECVE-2026-45345open-webui: IDOR allows unauthorized model modification6.50.2%open-webuiMay 14MEDIECVE-2026-45339Open WebUI: API key restriction bypass via header swap6.50.3%open-webuMay 14MEDIECVE-2026-45317Open-WebUI: CSRF image URL leaks session cookies4.60.2%open-webuiMay 14Frequently 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