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
2,377

AI/ML CVEs Tracked

337

Critical

392

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 337 results — Critical severity
Severity CVE ID Summary CVSS EPSS Package Date
CRIT CVE-2024-5959 Panel: Stored XSS enables session hijack in ML dashboards — 0.2% Panel Sep 18 CRIT CVE-2024-5958 Panel: SQL injection enables OS command execution — 0.5% Panel Sep 18 CRIT CVE-2024-6684 Nova Panel N7: auth bypass via alternate channel (EOL) — 0.6% inohom Nova Panel N7 Aug 12 CRIT E CVE-2024-41120 streamlit-geospatial: blind SSRF via unvalidated URL input 9.8 0.8% streamlit-geospatial Jul 26 CRIT E CVE-2024-41119 streamlit-geospatial: RCE via eval() on vis_params input 9.8 1.4% streamlit-geospatial Jul 26 CRIT E CVE-2024-41118 streamlit-geospatial: blind SSRF via WMS URL input 9.8 0.7% streamlit-geospatial Jul 26 CRIT E CVE-2024-41117 streamlit-geospatial: eval() injection allows RCE 9.8 1.3% streamlit-geospatial Jul 26 CRIT E CVE-2024-41116 streamlit-geospatial: RCE via eval() injection 9.8 1.3% streamlit-geospatial Jul 26 CRIT E CVE-2024-41115 streamlit-geospatial: eval() injection enables RCE 9.8 1.5% streamlit-geospatial Jul 26 CRIT E CVE-2024-41114 streamlit-geospatial: RCE via eval() on palette input 9.8 1.4% streamlit-geospatial Jul 26 CRIT E CVE-2024-41113 streamlit-geospatial: RCE via eval() in Timelapse page 9.8 1.4% streamlit-geospatial Jul 26 CRIT E CVE-2024-41112 streamlit-geospatial: RCE via eval() on palette input 9.8 1.4% streamlit-geospatial Jul 26 CRIT E CVE-2024-35198 TorchServe: URL bypass enables arbitrary model loading 9.8 0.8% torchserve Jul 19 CRIT E CVE-2024-39236 Gradio: code injection via component metadata (CVSS 9.8) 9.8 0.9% gradio Jul 1 CRIT E CVE-2024-37014 Langflow: unauthenticated RCE via custom component API 9.8 0.9% langflow Jun 10 CRIT E CVE-2024-3234 ChuanhuChatGPT: path traversal exposes LLM API keys 9.8 3.8% chuanhuchatgpt Jun 6 CRIT E CVE-2024-5452 pytorch-lightning: RCE via deepdiff Delta deserialization 9.8 26.5% pytorch_lightning Jun 6 CRIT E CVE-2024-4253 Gradio: CI/CD command injection enables secrets exfiltration 9.1 1.7% gradio Jun 4 CRIT E CVE-2024-34359 llama-cpp-python: SSTI in .gguf loader enables RCE 9.6 28.4% — May 14 CRIT E CVE-2024-3660 Keras: RCE via malicious model deserialization 9.8 1.7% keras Apr 16

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