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 485 results — High severity, no patchKeras: safe_mode bypass enables RCE via model load
CVE-2025-9906 Keras: safe_mode bypass enables RCE via .h5 model files
CVE-2025-9905 picklescan: file extension bypass allows model RCE
CVE-2025-10155 HuggingFace Transformers: ReDoS in MarianTokenizer
CVE-2025-6638 n8n: unrestricted file upload RCE via Chat Trigger
CVE-2025-56265 Langflow: privilege escalation to full superuser via CLI
CVE-2025-57760 vLLM: unauthenticated DoS via oversized HTTP header
CVE-2025-48956 Merlin Transformers4Rec: code injection via Python dep
CVE-2025-23298 Keras: safe mode bypass enables RCE via model load
CVE-2025-8747 WP Contest Gallery: Stored XSS exposes OpenAI API creds
CVE-2025-7725 lollms: timing attack enables credential enumeration
CVE-2025-6386 Transformers: ReDoS in chat.py causes CPU exhaustion
CVE-2025-3262 Langchain-Chatchat: path traversal exposes system files
CVE-2025-6855 Hive Support WP: OpenAI key theft + prompt hijack
CVE-2025-5018 jupyter_core: config hijack enables cross-user code exec
CVE-2025-30167 Gradio: unauthenticated file copy enables disk DoS
CVE-2025-48889 vLLM: image hash collision enables multimodal cache leakage
CVE-2025-46722 llama-index-cli: OS command injection enables RCE
CVE-2025-1753 label-studio-ml: PyTorch .pt deserialization RCE in YOLO loader
CVE-2025-5173 transformers: ReDoS in testing_utils causes DoS
CVE-2025-2099 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