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 1908 results — High severityCVE-2026-100532OpenClaw WhatsApp: missing owner check allows account disconnect8.10.3%openclawSep 26HIGHCVE-2026-89032LiteLLM: semantic cache tenant bypass leaks data7.70.3%litellmSep 25HIGHCVE-2026-83591AMP for WP: stored XSS via comment regex transform7.20.3%—Sep 25HIGHECVE-2026-61788DBHub: readonly mode bypass enables writes and RCE7.40.4%—Sep 24HIGHGHSA-g28h-2cmm-rj9xlangchain-nvidia: local file read via VLM image paths7.5—langchain-nvidia-ai-endpointsSep 24HIGHECVE-2026-77294TREK: SSRF via llm_base_url exposes cloud metadata8.10.3%—Sep 24HIGHCVE-2026-95521rpm: command injection via %() in src.rpm filenames7.8—rhoai/odh-mlflow-operator-rhel9Sep 24HIGHCVE-2026-95519rpm: macro expansion in manifest enables local code execution7.8—rhoai/odh-mlflow-operator-rhel9Sep 24HIGHECVE-2026-566769router: DNS rebinding SSRF in image prefetch7.40.2%9routerSep 23HIGHCVE-2026-96804MLflow: pickle deserialization RCE in statsmodels flavor8.80.7%mlflowSep 23HIGHCVE-2026-96775MLflow: dspy flavor pickle control bypass enables RCE8.80.6%mlflowSep 23HIGHCVE-2026-5695Microweber admin panel: unrestricted file upload to RCE—0.4%Administration panelSep 23HIGHECVE-2026-77247mcp-atlassian: arbitrary server file upload via path—0.4%mcp-atlassianSep 22HIGHECVE-2026-77262mcp-atlassian: path traversal enables arbitrary file read8.60.6%mcp-atlassianSep 22HIGHECVE-2026-77259mcp-atlassian: arbitrary file read via attachment upload7.70.4%mcp-atlassianSep 22HIGHECVE-2026-77257mcp-atlassian: arbitrary local file upload via path—0.4%mcp-atlassianSep 22HIGHECVE-2026-77255mcp-atlassian: arbitrary file read/exfil via attachments8.60.5%mcp-atlassianSep 22HIGHECVE-2026-77253mcp-atlassian: path traversal enables arbitrary file exfiltration7.10.4%mcp-atlassianSep 22HIGHECVE-2026-77246mcp-atlassian: unvalidated upload path leaks server files7.40.5%mcp-atlassianSep 22HIGHECVE-2026-77248mcp-atlassian: unauth file read via upload_attachment8.60.5%mcp-atlassianSep 22Frequently 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