AI Threat AlertAI 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 2876 results — no patchCVE-2025-2828LangChain RequestsToolkit: SSRF exposes cloud metadata10.021.0%langchainJun 23HIGHECVE-2025-34023Karel IP1211: path traversal exposes arbitrary files—1.6%—Jun 20LOWECVE-2025-6170libxml2: xmllint shell stack overflow causes local crash2.50.3%rhaiis/vllm-cuda-rhel9Jun 16HIGHCVE-2025-5018Hive Support WP: OpenAI key theft + prompt hijack7.10.3%—Jun 6CRITECVE-2025-1750LlamaIndex DuckDB: SQL injection enables file R/W and RCE9.80.9%llama-indexJun 2MEDIECVE-2025-48944vLLM: input validation DoS crashes inference worker6.50.6%vllmMay 30MEDIECVE-2025-48943vLLM: ReDoS crashes inference server via malformed regex6.50.5%vllmMay 30MEDIECVE-2025-48942vLLM: DoS via malformed JSON schema guided param6.50.6%vllmMay 30MEDIECVE-2025-48887vLLM: ReDoS in tool parser causes service outage6.50.5%vllmMay 30HIGHECVE-2025-48889Gradio: unauthenticated file copy enables disk DoS7.50.7%gradioMay 30HIGHCVE-2025-46722vLLM: image hash collision enables multimodal cache leakage7.30.3%vllmMay 29LOWCVE-2025-46570vLLM: timing side-channel leaks prompt cache data2.60.4%vllmMay 29LOWECVE-2025-5320Gradio: CORS origin bypass in ML UI handler3.70.3%gradioMay 29HIGHECVE-2025-1753llama-index-cli: OS command injection enables RCE7.81.1%llama-indexMay 28MEDICVE-2025-5278GNU Coreutils sort: heap under-read in begfield()4.4—rhoai/odh-llama-stack-k8s-operator-rhel9May 27HIGHCVE-2025-5173label-studio-ml: PyTorch .pt deserialization RCE in YOLO loader7.80.2%label-studio-mlMay 26CRITECVE-2025-47277vLLM: RCE via exposed TCPStore in distributed inference9.81.0%vllmMay 20HIGHECVE-2025-2099transformers: ReDoS in testing_utils causes DoS7.50.6%transformersMay 19UNKNECVE-2025-1975Ollama: DoS via malicious manifest in /api/pull—0.5%ollamaMay 16HIGHCVE-2025-0649TensorFlow Serving: JSON recursion DoS on inference API7.50.2%tensorflow_servingMay 6Frequently 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