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 533 results — Critical severityCVE-2024-41116streamlit-geospatial: RCE via eval() injection9.81.3%streamlit-geospatialJul 26CRITECVE-2024-41115streamlit-geospatial: eval() injection enables RCE9.81.5%streamlit-geospatialJul 26CRITECVE-2024-41114streamlit-geospatial: RCE via eval() on palette input9.81.4%streamlit-geospatialJul 26CRITECVE-2024-41113streamlit-geospatial: RCE via eval() in Timelapse page9.81.4%streamlit-geospatialJul 26CRITECVE-2024-41112streamlit-geospatial: RCE via eval() on palette input9.81.4%streamlit-geospatialJul 26CRITECVE-2024-35198TorchServe: URL bypass enables arbitrary model loading9.80.8%torchserveJul 19CRITCVE-2024-39700JupyterLab extension-template: CI workflow RCE10.01.1%extension-templateJul 16CRITECVE-2024-39236Gradio: code injection via component metadata (CVSS 9.8)9.80.9%gradioJul 1CRITECVE-2024-37014Langflow: unauthenticated RCE via custom component API9.863.7%langflowJun 10CRITECVE-2024-3234ChuanhuChatGPT: path traversal exposes LLM API keys9.83.8%chuanhuchatgptJun 6CRITECVE-2024-5452pytorch-lightning: RCE via deepdiff Delta deserialization9.826.8%pytorch_lightningJun 6CRITECVE-2024-4253Gradio: CI/CD command injection enables secrets exfiltration9.11.7%gradioJun 4CRITECVE-2024-34359llama-cpp-python: SSTI in .gguf loader enables RCE9.626.0%—May 14CRITECVE-2024-3660Keras: RCE via malicious model deserialization9.81.7%kerasApr 16CRITECVE-2024-3573MLflow: LFI via URI parsing allows arbitrary file read9.30.7%mlflowApr 16CRITECVE-2024-2912BentoML: RCE via insecure deserialization (CVSS 10)10.01.5%—Apr 16CRITECVE-2024-3568HuggingFace Transformers: RCE via pickle deserialization9.62.1%transformersApr 10CRITECVE-2024-31224gpt_academic: deserialization RCE, no auth required9.81.2%gpt_academicApr 8CRITECVE-2024-2057LangChain TFIDFRetriever: SSRF/RCE via load_local9.80.6%langchainMar 1CRITECVE-2024-27444LangChain Experimental: RCE via Python sandbox escape9.80.8%langchain-experimentalFeb 26Frequently 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