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 1908 results — High severityCVE-2026-58116LLaMA-Factory: RCE via malicious model path8.80.9%llama-factoryJun 30HIGHCVE-2026-58016GLib: malformed D-Bus XML integer overflow causes DoS7.5—rhoai/odh-llama-stack-k8s-operator-rhel9Jun 30HIGHECVE-2026-58014GLib: off-by-one in key file parser enables DoS7.30.6%rhaiis/vllm-cuda-rhel9Jun 30HIGHECVE-2026-14164libarchive: RAR5 double free enables remote DoS7.50.8%rhaii/vllm-gaudi-rhel9Jun 30HIGHECVE-2026-57947Pinpoint APM: SSRF via alarm webhook registration8.50.3%pinpointJun 29HIGHCVE-2026-55607Claude Code: worktree bug enables sandbox-escape RCE—0.7%@anthropic-ai/claude-codeJun 29HIGHECVE-2026-13484MLflow: missing authz in label schema CRUD API8.80.5%—Jun 28HIGHECVE-2026-57527ZAP: insecure deserialization RCE via ViewState add-on8.80.7%—Jun 26HIGHCVE-2026-5757Ollama: unauthenticated heap memory disclosure7.50.7%OllamaJun 26HIGHECVE-2025-71340picklescan: scanner bypass enables RCE via pickle supply chain8.10.4%picklescanJun 25HIGHECVE-2025-71335Flowise: password change fails to revoke sessions8.10.4%FlowiseJun 25HIGHECVE-2025-71328Flowise: unverified password change enables account takeover8.30.5%FlowiseJun 25HIGHECVE-2025-71324Flowise: path traversal leaks database unauthenticated7.51.6%FlowiseJun 25HIGHECVE-2026-554773X-UI: authenticated file write leads to RCE7.20.6%github.com/mhsanaei/3x-ui/v2Jun 25HIGHCVE-2026-56351n8n: SQL injection in DB nodes via identifier values8.20.4%n8nJun 24HIGHECVE-2026-56270Flowise: auth bypass exposes OAuth secrets in cleartext7.52.0%FlowiseJun 24HIGHECVE-2025-71361picklescan: scanner bypass allows RCE via pickle load8.10.4%picklescanJun 24HIGHECVE-2025-71354picklescan: scanner bypass enables arbitrary code execution8.10.4%picklescanJun 24HIGHCVE-2026-7574Claude Desktop: VM integrity bypass enables RCE8.70.1%Claude Desktop CoworkJun 23HIGHECVE-2026-55249@rtk-ai/rtk-rewrite: RCE via shell injection in exec tool8.80.6%openclawJun 23Frequently 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