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 12 of 512 results — has patchLabel Studio SDK: path traversal leaks server filesystem
CVE-2025-25295 LlamaFactory: RCE via OS command injection in training
CVE-2024-52803 Gradio: Dropdown validation bypass enables arbitrary input
GHSA-26jh-r8g2-6fpr ONNX: path traversal in model download enables RCE
CVE-2024-5187 langchain-community: DoS via recursive sitemap loop
CVE-2024-2965 Ray: unauthenticated LFI exposes entire filesystem
CVE-2023-6020 Ray: unauthenticated RCE via dashboard command injection
CVE-2023-6019 Ray: LFI allows unauthenticated file read
CVE-2023-6021 LangChain: prompt injection → SQL RCE (CVSS 9.8)
CVE-2023-32785 Label Studio: SSRF + file read, self-reg bypass
CVE-2022-36551 Jupyter Notebook: XSS via missing CSP on served files
CVE-2018-21030 Jupyter Notebook: XSS via malicious .ipynb file
CVE-2018-8768 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