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 4307 resultsCVE-2026-110695ExLlamaV2: heap overflow in safetensors loader6.30.4%—Oct 14MEDIECVE-2026-110689OpenClaw ClawScan: scanner path-skip bypass evades detection5.30.1%openclawOct 14MEDICVE-2026-110248SageMaker SDK: git clone error leaks repo credentials to logs5.30.5%sagemakerOct 14MEDIECVE-2026-102756DataEase: stored XSS via chart axis label tooltip—0.4%—Oct 14HIGHCVE-2026-104103Ludwig: tar symlink path traversal allows arbitrary file write8.10.5%—Oct 14HIGHECVE-2026-110719Portkey Gateway: SSRF via custom host header7.20.4%—Oct 14LOWCVE-2026-60008Gitea: notebook CSS class injection enables UI redress3.50.4%—Oct 14MEDICVE-2026-110257OW2 ASM: crafted class file triggers 2GB allocation DoS5.50.2%—Oct 14HIGHECVE-2026-86022VNote: argument injection in external program launch7.00.2%—Oct 13HIGHCVE-2026-86063Claude Code: unverified plugin SHA checkout enables code install—0.2%claude-codeOct 13HIGHCVE-2026-109429Mistral Vibe: bash gate bypass allows silent RCE8.80.6%mistral-vibeOct 13HIGHCVE-2026-109428Mistral Vibe: bash parsing bypass allows hidden commands8.80.5%mistral-vibeOct 13MEDICVE-2026-102832JupyterLab: trust prompt race marks wrong document trusted4.20.1%jupyterlite-coreOct 13MEDIECVE-2026-108954sherpa-onnx: buffer overflow via unvalidated model metadata6.30.3%sherpa-onnxOct 13HIGHECVE-2026-109572Open WebUI: terminal proxy privilege escalation7.60.3%open-webuiOct 12HIGHECVE-2026-84317Nginx UI: MCP config_add bypasses directive validation8.80.5%—Oct 12HIGHECVE-2026-109557EdgeEver: stored XSS via MCP names steals bridge token8.70.4%—Oct 12MEDICVE-2024-58389HoloViz Panel: open redirect via login next parameter6.10.3%panelOct 12HIGHECVE-2026-57143PraisonAI: SSRF via LLM-controlled SearxNG URL8.80.3%praisonaiagentsOct 12CRITECVE-2026-57118PraisonAI agents: unauthenticated access to agent endpoints9.80.4%praisonaiagentsOct 12Frequently 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