AI Threat Alert AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,625

AI/ML CVEs Tracked

230

Critical

87

New This Week

16

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 1625 results
Severity CVE ID Summary CVSS EPSS Package Date
HIGH CVE-2026-44556 open-webui: auth bypass allows unrestricted model access 7.1 — open-webui May 8 HIGH CVE-2026-44555 open-webui: access control bypass via model chaining 7.6 — open-webui May 8 HIGH CVE-2026-44552 open-webui: Redis cache poisoning enables cross-instance tool hijack 8.7 — open-webui May 8 HIGH CVE-2026-44553 open-webui: stale Socket.IO role allows cross-user note R/W 8.1 — open-webui May 8 MEDI CVE-2026-44550 open-webui: mass assignment enables cross-user folder injection 5.0 — open-webui May 8 CRIT CVE-2026-44551 open-webui: LDAP auth bypass — full account takeover 9.1 — open-webui May 8 HIGH CVE-2026-44721 open-webui: XSS in model descriptions steals session tokens 7.3 — open-webui May 8 HIGH GHSA-8g7g-hmwm-6rv2 n8n-mcp: path traversal + SSRF exposes n8n API keys 8.3 — n8n-mcp May 8 UNKN CVE-2026-44694 n8n-MCP: SSRF allows internal network access via webhook tools — 0.0% n8n-mcp May 8 HIGH CVE-2026-42271 LiteLLM: RCE via MCP test endpoint command injection 8.8 0.1% litellm May 8 CRIT E CVE-2026-42208 LiteLLM: SQL injection exposes LLM API credentials 9.8 37.4% litellm May 8 UNKN CVE-2026-42203 LiteLLM: SSTI in prompt template endpoint enables RCE — 0.0% litellm May 8 MEDI CVE-2026-40610 BentoML: symlink traversal exfiltrates host secrets at build 5.5 — bentoml May 7 HIGH CVE-2026-44513 diffusers: trust_remote_code bypass enables silent RCE 8.8 — diffusers May 7 CRIT CVE-2026-44007 vm2: sandbox escape via nesting:true enables RCE 9.1 — vm2 May 7 HIGH GHSA-j7w6-vpvq-j3gm diffusers: silent RCE via None.py trust_remote_code bypass 8.8 — diffusers May 7 HIGH CVE-2026-44504 Aegra: cross-tenant IDOR hijacks user thread data — — aegra-api May 7 CRIT CVE-2026-44484 pytorch-lightning: supply chain, credential harvesting — — pytorch-lightning May 7 MEDI CVE-2026-44479 vercel: auth token leak in AI agent non-interactive mode 5.5 — — May 7 MEDI GHSA-cqmh-pcgr-q42f @axonflow/openclaw: credential exposure via insecure file permissions 5.5 — @axonflow/openclaw May 6

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