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 1431 results — has patchCVE-2024-11958llama-index DuckDB retriever: SQLi enables RCE9.81.4%llama-index-retrievers-duckdb-retrieverMar 20MEDIECVE-2024-10940langchain-core: file read via prompt template inputs5.30.4%langchain-coreMar 20HIGHCVE-2024-10188litellm: unauthenticated DoS crashes LLM proxy server7.50.6%litellmMar 20MEDIECVE-2025-1944picklescan: ZIP spoof lets malicious PyTorch models bypass scan6.50.3%picklescanMar 10MEDICVE-2025-1979Ray: Redis password exposed via plaintext logging6.40.2%rayMar 6CRITECVE-2025-25362spacy-llm: SSTI allows unauthenticated RCE (CVSS 9.8)9.80.8%spacy-llmMar 5MEDIECVE-2025-1716picklescan: scanner bypass enables supply chain RCE—1.7%picklescanMar 3MEDIECVE-2025-1889picklescan: extension bypass enables RCE on model load—0.4%picklescanMar 3CRITCVE-2023-25574JupyterHub LTI13: JWT forgery enables full auth bypass10.00.4%jupyterhub-ltiauthenticatorFeb 25HIGHCVE-2025-25297Label Studio: SSRF via S3 endpoint exposes internal services8.60.7%label-studioFeb 14MEDIECVE-2025-25296Label Studio: reflected XSS via label_config param6.11.9%label-studioFeb 14HIGHECVE-2025-25295Label Studio SDK: path traversal leaks server filesystem—0.8%label-studio-sdkFeb 14MEDIECVE-2024-53526Composio: command injection in AI agent tool calls6.40.6%composio-openaiJan 8CRITECVE-2024-52803LlamaFactory: RCE via OS command injection in training9.82.3%llamafactoryNov 21MEDICVE-2024-52524Giskard: ReDoS in text perturbation causes DoS—0.8%giskardNov 14HIGHCVE-2024-49048TorchGeo: RCE via code injection in geospatial ML lib8.11.2%torchgeoNov 12MEDIGHSA-26jh-r8g2-6fprGradio: Dropdown validation bypass enables arbitrary input5.3—gradioOct 10MEDIECVE-2024-7041open-webui: IDOR enables cross-user memory tampering6.50.4%open-webuiOct 9MEDIECVE-2024-6706Open WebUI: prompt-driven XSS runs attacker JavaScript6.10.7%open-webuiAug 8HIGHECVE-2024-5187ONNX: path traversal in model download enables RCE8.81.2%onnxJun 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