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 1961 results — Active exploitationCVE-2026-27825mcp-atlassian: Path Traversal enables file access9.112.3%mcp-atlassianMar 10HIGHECVE-2026-27826mcp-atlassian: SSRF allows internal network access8.213.9%mcp-atlassianMar 10CRITECVE-2026-25960vllm: SSRF allows internal network access9.80.6%vllmMar 9CRITECVE-2026-30824Flowise: auth bypass exposes NVIDIA NIM container endpoints9.837.3%flowiseMar 7UNKNECVE-2026-30823Flowise: IDOR enables account takeover and SSO bypass—0.5%flowiseMar 7UNKNECVE-2026-30822Flowise: mass assignment allows unauthenticated DB injection—15.0%flowiseMar 7CRITECVE-2026-30821flowise: Arbitrary File Upload enables RCE9.816.7%flowiseMar 7HIGHECVE-2026-30820Flowise: header spoof auth bypass exposes admin API & creds8.80.5%flowiseMar 7HIGHECVE-2026-25048xgrammar: security flaw enables exploitation7.51.3%xgrammarMar 5HIGHECVE-2026-0847NLTK: path traversal exposes sensitive server files8.61.0%—Mar 4HIGHECVE-2026-27905bentoml: security flaw enables exploitation7.80.3%bentomlMar 3HIGHECVE-2026-28416gradio: SSRF allows internal network access8.67.3%gradioFeb 27HIGHECVE-2026-28414gradio: security flaw enables exploitation7.53.1%gradioFeb 27MEDIECVE-2026-27167gradio: Weak Credentials allow account compromise5.90.5%gradioFeb 27CRITECVE-2026-27966langflow: Code Injection enables RCE9.835.2%langflowFeb 26HIGHECVE-2026-2472google-cloud-aiplatform: XSS enables session hijacking8.10.6%google-cloud-aiplatformFeb 20MEDIECVE-2026-27482ray: Missing Auth allows unauthenticated access5.90.3%rayFeb 20HIGHECVE-2026-26286sillytavern: SSRF allows internal network access8.50.3%—Feb 19LOWECVE-2026-24764OpenClaw: indirect prompt injection via Slack metadata3.70.2%openclawFeb 19CRITECVE-2026-2654smolagents: SSRF allows internal network access9.80.4%smolagentsFeb 18Frequently 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