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
2,390

AI/ML CVEs Tracked

342

Critical

304

New This Week

18

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 826 results — has patch
Severity CVE ID Summary CVSS EPSS Package Date
MEDI CVE-2026-34446 ONNX: hardlink path traversal leaks sensitive files 4.7 0.2% onnx Apr 1 HIGH CVE-2026-34445 ONNX: property overwrite via crafted model file 8.6 0.3% onnx Apr 1 UNKN E CVE-2026-27489 ONNX: symlink path traversal allows arbitrary file read — 0.5% onnx Mar 31 MEDI CVE-2026-34452 Anthropic SDK: TOCTOU symlink escape in async memory tool — 0.1% anthropic Mar 31 MEDI CVE-2026-34451 anthropic-ai/sdk: memory tool path traversal escape — 0.3% @anthropic-ai/sdk Mar 31 MEDI CVE-2026-34450 anthropic-sdk: insecure file perms expose agent memory — 0.1% anthropic Mar 31 CRIT E CVE-2026-0596 MLflow: command injection via model_uri in mlserver mode 9.6 1.3% mlflow Mar 31 HIGH GHSA-m3mh-3mpg-37hw OpenClaw: .npmrc hijack enables RCE on plugin install 8.6 — openclaw Mar 30 MEDI GHSA-68f8-9mhj-h2mp OpenClaw: HTTP scope bypass enables model enumeration — — openclaw Mar 30 HIGH GHSA-hr5v-j9h9-xjhg OpenClaw: sandbox escape via mediaUrl path traversal 7.7 — openclaw Mar 30 CRIT E CVE-2025-15379 MLflow: RCE via unsanitized model dependency specs 10.0 2.4% mlflow Mar 30 CRIT E CVE-2025-15036 MLflow: path traversal enables sandbox escape, file overwrite 9.6 0.5% mlflow Mar 30 MEDI CVE-2026-35646 openclaw: webhook rate-limit bypass enables token brute-force 4.8 0.2% openclaw Mar 29 MEDI CVE-2026-35640 openclaw: unauthenticated webhook parsing enables DoS 5.3 0.4% openclaw Mar 29 HIGH CVE-2026-35629 openclaw: SSRF in channel extensions hits internal network 7.4 0.2% openclaw Mar 29 MEDI CVE-2026-35657 openclaw: auth bypass exposes agent session history via HTTP 6.5 0.2% openclaw Mar 29 UNKN CVE-2026-34046 Langflow: IDOR exposes flows and plaintext API keys — 0.4% langflow Mar 27 UNKN CVE-2026-33873 Langflow: server-side RCE via LLM-generated code exec — 1.4% langflow Mar 27 HIGH E CVE-2026-34070 langchain-core: path traversal exposes host secrets via prompt config 7.5 1.1% langchain-core Mar 27 HIGH E CVE-2026-33989 @mobilenext/mobile-mcp: path traversal via AI agent tool 8.1 0.5% @mobilenext/mobile-mcp Mar 27

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