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.
- 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 826 results — has patch CVE-2024-11958 llama-index DuckDB retriever: SQLi enables RCE 9.8 1.3% llama-index-retrievers-duckdb-retriever Mar 20 MEDI E CVE-2024-10940 langchain-core: file read via prompt template inputs 5.3 0.4% langchain-core Mar 20 HIGH CVE-2024-10188 litellm: unauthenticated DoS crashes LLM proxy server 7.5 0.5% litellm Mar 20 MEDI E CVE-2025-1944 picklescan: ZIP spoof lets malicious PyTorch models bypass scan 6.5 0.3% picklescan Mar 10 MEDI CVE-2025-1979 Ray: Redis password exposed via plaintext logging 6.4 0.2% ray Mar 6 CRIT E CVE-2025-25362 spacy-llm: SSTI allows unauthenticated RCE (CVSS 9.8) 9.8 0.7% spacy-llm Mar 5 MEDI E CVE-2025-1716 picklescan: scanner bypass enables supply chain RCE — 1.5% picklescan Mar 3 MEDI E CVE-2025-1889 picklescan: extension bypass enables RCE on model load — 0.4% picklescan Mar 3 CRIT CVE-2023-25574 JupyterHub LTI13: JWT forgery enables full auth bypass 10.0 0.3% jupyterhub-ltiauthenticator Feb 25 HIGH CVE-2025-25297 Label Studio: SSRF via S3 endpoint exposes internal services 8.6 0.5% label-studio Feb 14 MEDI E CVE-2025-25296 Label Studio: reflected XSS via label_config param 6.1 1.8% label-studio Feb 14 HIGH E CVE-2025-25295 Label Studio SDK: path traversal leaks server filesystem — 0.7% label-studio-sdk Feb 14 MEDI E CVE-2024-53526 Composio: command injection in AI agent tool calls 6.4 0.6% composio-openai Jan 8 CRIT E CVE-2024-52803 LlamaFactory: RCE via OS command injection in training 9.8 2.3% llamafactory Nov 21 MEDI CVE-2024-52524 Giskard: ReDoS in text perturbation causes DoS — 0.8% giskard Nov 14 HIGH CVE-2024-49048 TorchGeo: RCE via code injection in geospatial ML lib 8.1 1.2% torchgeo Nov 12 MEDI GHSA-26jh-r8g2-6fpr Gradio: Dropdown validation bypass enables arbitrary input 5.3 — gradio Oct 10 HIGH E CVE-2024-5187 ONNX: path traversal in model download enables RCE 8.8 1.2% onnx Jun 6 MEDI E CVE-2024-2965 langchain-community: DoS via recursive sitemap loop 4.2 0.3% langchain Jun 6 CRIT E CVE-2023-6020 Ray: unauthenticated LFI exposes entire filesystem 9.3 14.7% ray Nov 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