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 4330 resultsCVE-2025-15379MLflow: RCE via unsanitized model dependency specs10.02.4%mlflowMar 30HIGHECVE-2026-5121libarchive: integer overflow in zisofs hits vllm containers7.51.1%rhaiis/vllm-cuda-rhel9Mar 30CRITECVE-2025-15036MLflow: path traversal enables sandbox escape, file overwrite9.60.6%mlflowMar 30MEDICVE-2026-35646openclaw: webhook rate-limit bypass enables token brute-force4.80.2%openclawMar 29MEDICVE-2026-35640openclaw: unauthenticated webhook parsing enables DoS5.30.4%openclawMar 29HIGHCVE-2026-35629openclaw: SSRF in channel extensions hits internal network7.40.2%openclawMar 29MEDICVE-2026-35657openclaw: auth bypass exposes agent session history via HTTP6.50.2%openclawMar 29HIGHCVE-2026-33575OpenClaw: gateway credential exposed in pairing setup codes7.50.3%OpenClawMar 29MEDICVE-2026-33574OpenClaw: TOCTOU path traversal enables arbitrary file write6.20.1%OpenClawMar 29HIGHCVE-2026-33573OpenClaw: workspace boundary bypass, arbitrary exec8.80.3%OpenClawMar 29HIGHCVE-2026-33572OpenClaw: insecure transcript files expose agent secrets8.40.1%OpenClawMar 29CRITCVE-2026-32987OpenClaw: bootstrap code replay escalates to operator.admin9.80.4%OpenClawMar 29HIGHCVE-2026-32980OpenClaw: unauthenticated webhook DoS via body buffering7.50.5%OpenClawMar 29HIGHCVE-2026-32979OpenClaw: TOCTOU race enables local code execution7.30.1%OpenClawMar 29HIGHCVE-2026-32978OpenClaw: script approval bypass allows RCE8.00.2%OpenClawMar 29CRITCVE-2026-32975OpenClaw: auth bypass via group name spoofing in agent9.80.3%OpenClawMar 29HIGHCVE-2026-32974OpenClaw: auth bypass triggers forged webhook tool execution8.60.3%OpenClawMar 29CRITCVE-2026-32973OpenClaw: exec allowlist bypass enables RCE9.80.4%OpenClawMar 29HIGHCVE-2026-32972OpenClaw: auth bypass enables persistent CDP backdoor7.10.3%OpenClawMar 29CRITCVE-2026-32924OpenClaw: auth bypass via Feishu reaction misclassification9.80.3%OpenClawMar 29Frequently 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