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 1961 results — Active exploitationCVE-2026-55255Langflow: IDOR allows cross-user flow execution9.90.9%langflowJun 19HIGHECVE-2026-54528jupyterlab-git: excluded_paths bypass exposes secrets7.10.4%jupyterlab-gitJun 19CRITECVE-2026-54527jupyterlab-git: stored XSS escalates to full RCE9.00.5%@jupyterlab/gitJun 19HIGHECVE-2026-54499Stanza: pickle fallback bypass enables model RCE7.50.5%torchJun 19HIGHECVE-2026-54317Home Assistant Konnected: auth bypass leaks alarm panel state7.60.3%homeassistantJun 19MEDIECVE-2026-49345Mercator: SSRF enables internal network RCE via gopher://—0.6%—Jun 19HIGHECVE-2026-56211libaom: AV1 SVC OOB write enables RCE7.10.9%rhaiis/vllm-cpu-rhel9Jun 19MEDIECVE-2026-55832tract-onnx: path traversal exposes arbitrary local files6.10.2%tract-onnxJun 19MEDIECVE-2026-55414nl-portal: GraphQL SSRF exposes Objecten-API auth token5.30.4%nl.nl-portal:formJun 19HIGHECVE-2026-56078PraisonAI: path traversal → arbitrary file read/write/RCE8.80.9%PraisonAIJun 18MEDIECVE-2026-56077PraisonAI: agent ID collision leaks system prompts6.50.4%PraisonAIJun 18HIGHECVE-2026-56076PraisonAI: CORS bypass enables arbitrary agent execution8.10.6%PraisonAIJun 18HIGHECVE-2026-56075PraisonAI: RCE via hardcoded approval_mode bypass8.80.6%PraisonAIJun 18MEDIECVE-2026-56074PraisonAI: tool approval bypass enables credential theft5.50.2%PraisonAIJun 18MEDIECVE-2026-54683nl-portal documenten-api: IDOR exposes citizen documents6.50.4%nl.nl-portal:documenten-apiJun 18CRITECVE-2026-55450Langflow: unauthenticated upload → DoS + path disclosure9.31.2%langflowJun 17MEDIECVE-2026-54022open-webui: Yjs auth bypass exposes all user notes5.30.3%open-webuiJun 17MEDIECVE-2026-54019open-webui: RAG ACL bypass exposes private KB chunks6.50.4%open-webuiJun 17HIGHECVE-2026-54018open-webui: SSRF via redirect bypass in Playwright loader7.70.4%open-webuiJun 17HIGHECVE-2026-54017open-webui: double-encoded path traversal in terminal proxy7.70.5%open-webuiJun 17Frequently 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