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 533 results — Critical severityCVE-2026-12940Langflow: unauth RCE via MCP env var injection9.80.9%langflowJul 30CRITCVE-2026-13435Langflow: PythonREPL sandbox escape enables RCE9.90.5%Langflow OSSJul 30CRITECVE-2026-67429flyto-core: arbitrary file write via bypassed path guard10.00.6%—Jul 30CRITCVE-2026-58046Plesk XML-RPC: blind SQLi exposes full panel DB9.90.6%—Jul 30CRITGHSA-mqhr-6j6h-74p5Budibase: unauth SSRF leaks stored REST API credentials——@budibase/serverJul 24CRITECVE-2026-65700h2oGPT: unauth path traversal in files API leads to RCE9.81.5%h2ogptJul 23CRITECVE-2026-65007Grav CMS API plugin: forged keys enable account takeover9.60.3%—Jul 21CRITECVE-2026-63766GPT-SoVITS: unauthenticated RCE via webui.py9.82.1%—Jul 20CRITECVE-2026-63767ktransformers: unauth pickle RCE via ZMQ socket9.81.1%ktransformersJul 20CRITCVE-2026-13446Langflow: hard-coded credentials enable takeover9.80.4%langflowJul 17CRITCVE-2026-8859Langflow: path traversal writes arbitrary files9.90.6%langflowJul 17CRITCVE-2026-8635Langflow: DB manipulation escalates to superuser RCE9.90.6%langflowJul 17CRITCVE-2026-8505Langflow: webhook auth bypass enables unauth RCE9.80.9%langflowJul 17CRITCVE-2026-8481Langflow: unsandboxed exec() enables full RCE9.90.9%langflowJul 17CRITCVE-2026-8476Langflow: pickle deserialization RCE via disk cache (CVSS 9.9)9.91.0%langflowJul 17CRITCVE-2026-13448Langflow: unauthenticated RCE via public flow endpoint9.80.7%langflowJul 17CRITCVE-2026-9135Langflow: code injection bypasses ToolGuard, enables RCE9.90.8%langflowJul 17CRITECVE-2026-9103Langflow: unauth request grants superuser token9.83.2%langflowJul 17CRITCVE-2026-9198Langflow: token forgery + exec() chain to RCE9.828.7%Langflow OSSJul 17CRITCVE-2026-9202Langflow: unauth signup chains to RCE9.80.5%Langflow OSSJul 17Frequently 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