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 severityGHSA-846p-hgpv-vphcOpenClaw: path traversal → host file exfiltration via QQ Bot——openclawApr 7MEDIGHSA-m34q-h93w-vg5xopenclaw: path traversal enables remote dir overwrite——openclawApr 7MEDIGHSA-wwfp-w96m-c6x8OpenClaw: pairing DoS blocks account onboarding——openclawApr 7MEDIGHSA-h43v-27wg-5mf9OpenClaw: pre-auth signature bypass enables pairing DoS——openclawApr 7MEDIGHSA-wpc6-37g7-8q4wOpenClaw: exec allowlist bypass via shell init-file options——openclawApr 7MEDIGHSA-42mx-vp8m-j7qhopenclaw: sandbox escape via mirror mode hook execution——openclawApr 7MEDIGHSA-fwjq-xwfj-gv75openclaw: auth bypass exposes agent session visibility——openclawApr 7MEDIGHSA-3q42-xmxv-9vfropenclaw: privilege escalation to admin voice config persistence——openclawApr 7MEDIGHSA-vjx8-8p7h-82gropenclaw: SSRF in marketplace plugin download——openclawApr 7MEDIGHSA-4g5x-2jfc-xm98openclaw: media download bypass exhausts disk storage——openclawApr 7MEDIGHSA-h2v7-xc88-xx8copenclaw: operator scope bypass in phone arm/disarm cmds——openclawApr 7MEDICVE-2026-5745libarchive: NULL deref in ACL parsing causes DoS5.5—rhoai/odh-mlflow-operator-rhel9Apr 7MEDIECVE-2026-33866MLflow: auth bypass exposes model artifacts across experiments4.30.4%mlflowApr 7MEDIECVE-2026-33865MLflow: stored XSS via MLmodel YAML artifact upload—0.2%mlflowApr 7MEDIECVE-2026-1839HuggingFace Transformers: RCE via malicious checkpoint load6.50.4%transformersApr 7MEDICVE-2026-34425OpenClaw: script preflight bypass enables unsafe exec—0.3%openclawApr 6MEDIECVE-2026-35492kedro-datasets: path traversal enables arbitrary file write6.50.4%kedro-datasetsApr 6MEDICVE-2026-5530Ollama: SSRF in Model Pull API enables network pivot6.30.3%—Apr 5MEDIGHSA-mvv8-v4jj-g47jDirectus: cleartext storage exposes AI API keys6.5——Apr 4MEDICVE-2026-34755vLLM: OOM DoS via unbounded video frame decoding6.50.5%vllmApr 3Frequently 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