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.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
3,021

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 1321 results — High severity
Severity CVE ID Summary CVSS EPSS Package Date
HIGH GHSA-g5r6-gv6m-f5jv mcp-atlassian: path traversal leaks secrets via injection 7.7 — mcp-atlassian Jul 10 HIGH GHSA-wm45-qh3g-v83f mcp-atlassian: path traversal leaks server files+creds 7.7 — mcp-atlassian Jul 10 HIGH CVE-2026-54070 SiYuan: XSS in Bazaar README steals admin API token 7.1 0.2% github.com/siyuan-note/siyuan/kernel Jul 10 HIGH E CVE-2026-54066 SiYuan: /assets path traversal exposes API secrets 7.5 1.9% github.com/siyuan-note/siyuan/kernel Jul 10 HIGH E CVE-2026-61437 PraisonAI: unsafe dynamic import enables RCE 7.8 0.1% praisonaiagents Jul 10 HIGH E CVE-2026-61434 PraisonAI: allowlist bypass enables RCE via find -exec 8.8 0.6% praisonai Jul 10 HIGH E CVE-2026-60091 PraisonAI: SSRF via webhook_url DNS rebinding 7.2 0.2% praisonai Jul 10 HIGH E CVE-2026-59221 Open WebUI: encoded path traversal in terminal proxy 7.7 0.4% open-webui Jul 9 HIGH CVE-2026-59224 Open WebUI: terminal proxy allows user ID spoofing 8.0 0.3% open-webui Jul 9 HIGH E CVE-2026-59216 Open WebUI: session hijack enables cross-user code exec 7.7 0.3% open-webui Jul 9 HIGH E CVE-2026-59219 Open WebUI: revoked JWTs bypass WebSocket auth 7.1 0.3% open-webui Jul 9 HIGH CVE-2026-59206 n8n: prototype pollution lets guests hit admin APIs 7.1 0.4% n8n Jul 9 HIGH CVE-2026-59214 Open WebUI: Pyodide sandbox bypass reaches admin RCE 7.3 0.3% open-webui Jul 9 HIGH GHSA-52vm-mxx8-f227 Phantom MCP: unconfined output path enables file write 7.7 — — Jul 9 HIGH E CVE-2026-59723 Cline: missing Origin check on Hub enables RCE 8.8 0.1% cline Jul 8 HIGH E CVE-2026-49471 Serena: unauth dashboard API enables RCE via memory poisoning 8.3 0.3% serena-agent Jul 8 HIGH CVE-2026-59822 LiteLLM: MCP auth bypass via fabricated OAuth header 8.2 0.3% litellm Jul 8 HIGH CVE-2026-59821 LiteLLM: code exec via unsandboxed Custom Guardrails 7.2 0.4% litellm Jul 8 HIGH E CVE-2026-59806 Gradio: SSRF via file_fetch() leaks cloud IAM creds 7.4 0.2% gradio Jul 8 HIGH CVE-2026-59257 n8n: SQL injection via MySQL v1 node expressions 8.8 0.3% n8n Jul 8

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