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-2026-12945Langflow: IDOR exposes/manipulates other users' builds7.10.4%langflowJul 30CRITCVE-2026-12940Langflow: unauth RCE via MCP env var injection9.80.9%langflowJul 30MEDICVE-2026-10700Langflow: IDOR in file API leaks cross-tenant data6.50.5%Langflow OSSJul 30CRITCVE-2026-13435Langflow: PythonREPL sandbox escape enables RCE9.90.5%Langflow OSSJul 30HIGHCVE-2026-12942Langflow: path traversal exposes arbitrary server files7.50.6%Langflow OSSJul 30CRITECVE-2026-67429flyto-core: arbitrary file write via bypassed path guard10.00.6%—Jul 30HIGHCVE-2026-12722FTC E-Commerce Panel: authentication bypass8.20.4%—Jul 30CRITCVE-2026-58046Plesk XML-RPC: blind SQLi exposes full panel DB9.90.6%—Jul 30MEDICVE-2026-54249Pydantic AI: UploadedFile refs leak cloud storage6.80.3%pydantic-aiJul 29HIGHCVE-2026-18022pgvector: integer wraparound in index build enables RCE8.80.6%pgvectorJul 29HIGHECVE-2026-67428Flyto2 Core: SSRF via unvalidated URLs in agent tools8.50.4%flyto-coreJul 29HIGHECVE-2026-67425Flyto2 Core: SSRF leaks LLM API keys via base_url8.60.4%flyto-coreJul 29HIGHECVE-2026-50559Quarkus: HTTP auth bypass via %3B/%2F path smuggling7.51.0%io.quarkus:quarkus-vertx-httpJul 29LOWGHSA-pc2w-4mq8-32qwDynatrace MCP: notebook tool skips approval gate3.7—@dynatrace-oss/dynatrace-mcp-serverJul 29HIGHCVE-2026-13442Langflow: FAISS namespace reuse leaks cross-user vectors7.10.3%langflowJul 28HIGHECVE-2026-54593Pterodactyl Wings: JWT reuse enables file upload bypass8.10.7%github.com/pterodactyl/wingsJul 28HIGHECVE-2026-61609Pterodactyl Panel: global rate limiter enables panel-wide login DoS7.50.5%pterodactyl/panelJul 28MEDICVE-2026-16773WPBot: unauth PII exfil via chat transcript flaw5.30.5%WPBot – AI ChatBot for Live Support, Lead Generation, AI ServicesJul 28MEDICVE-2026-16774WPBot: unauthenticated email abuse via wp_mail()5.30.4%WPBot – AI ChatBot for Live Support, Lead Generation, AI ServicesJul 28LOWECVE-2026-14189WPBot: admin-set field IDs enable stored SQLi3.80.3%wpbotJul 27Frequently 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