AI Threat Alert
AI 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 424 results — Critical severity CVE-2026-13435 Langflow: PythonREPL sandbox escape enables RCE 9.9 0.3% Langflow OSS Jul 30 CRIT E CVE-2026-67429 flyto-core: arbitrary file write via bypassed path guard 10.0 0.5% — Jul 30 CRIT CVE-2026-58046 Plesk XML-RPC: blind SQLi exposes full panel DB 9.9 0.3% — Jul 30 CRIT GHSA-mqhr-6j6h-74p5 Budibase: unauth SSRF leaks stored REST API credentials — — @budibase/server Jul 24 CRIT E CVE-2026-65700 h2oGPT: unauth path traversal in files API leads to RCE 9.8 1.3% h2ogpt Jul 23 CRIT E CVE-2026-65007 Grav CMS API plugin: forged keys enable account takeover 9.6 0.3% — Jul 21 CRIT E CVE-2026-63766 GPT-SoVITS: unauthenticated RCE via webui.py 9.8 1.7% — Jul 20 CRIT CVE-2026-63767 ktransformers: unauth pickle RCE via ZMQ socket 9.8 0.7% ktransformers Jul 20 CRIT CVE-2026-13446 Langflow: hard-coded credentials enable takeover 9.8 0.2% langflow Jul 17 CRIT CVE-2026-8859 Langflow: path traversal writes arbitrary files 9.9 0.4% langflow Jul 17 CRIT CVE-2026-8635 Langflow: DB manipulation escalates to superuser RCE 9.9 0.3% langflow Jul 17 CRIT CVE-2026-8505 Langflow: webhook auth bypass enables unauth RCE 9.8 0.6% langflow Jul 17 CRIT CVE-2026-8481 Langflow: unsandboxed exec() enables full RCE 9.9 0.5% langflow Jul 17 CRIT CVE-2026-8476 Langflow: pickle deserialization RCE via disk cache (CVSS 9.9) 9.9 0.5% langflow Jul 17 CRIT CVE-2026-13448 Langflow: unauthenticated RCE via public flow endpoint 9.8 0.5% langflow Jul 17 CRIT CVE-2026-9135 Langflow: code injection bypasses ToolGuard, enables RCE 9.9 0.4% langflow Jul 17 CRIT CVE-2026-9103 Langflow: unauth request grants superuser token 9.8 0.4% langflow Jul 17 CRIT E CVE-2026-9198 Langflow: token forgery + exec() chain to RCE 9.8 17.1% Langflow OSS Jul 17 CRIT CVE-2026-9202 Langflow: unauth signup chains to RCE 9.8 0.3% Langflow OSS Jul 17 CRIT E CVE-2026-54458 AVideo: stored XSS in YPTSocket enables admin takeover 9.6 0.3% — Jul 15 Frequently 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