AI Security Threat Feed
Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 512 results — has patchSageMaker SDK: MD5 collision silently replaces ML workflows
CVE-2025-0508 LiteLLM: API key leakage in logs exposes credentials
CVE-2024-9606 litellm: unauthenticated DoS via multipart boundary parsing
CVE-2024-8984 OpenWebUI: path traversal RCE via audio upload API
CVE-2024-8060 Open-WebUI: CSRF enables RCE via pipeline code injection
CVE-2024-7806 ONNX: path traversal in download_model enables RCE
CVE-2024-7776 pytorch-lightning: file upload RCE (Windows)
CVE-2024-8019 open-webui: DoS via malformed multipart boundary
GHSA-6wj5-5pgr-jwq8 lollms: RCE via eval() sandbox bypass in Calculate
CVE-2024-6982 llama-index: DoS via infinite recursion in web reader
CVE-2024-12910 llama-index DuckDB retriever: SQLi enables RCE
CVE-2024-11958 langchain-core: file read via prompt template inputs
CVE-2024-10940 litellm: unauthenticated DoS crashes LLM proxy server
CVE-2024-10188 picklescan: ZIP spoof lets malicious PyTorch models bypass scan
CVE-2025-1944 Ray: Redis password exposed via plaintext logging
CVE-2025-1979 spacy-llm: SSTI allows unauthenticated RCE (CVSS 9.8)
CVE-2025-25362 picklescan: scanner bypass enables supply chain RCE
CVE-2025-1716 picklescan: extension bypass enables RCE on model load
CVE-2025-1889 Label Studio: SSRF via S3 endpoint exposes internal services
CVE-2025-25297 Label Studio: reflected XSS via label_config param
CVE-2025-25296 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
AI Threat Alert