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 4330 resultsCVE-2026-45224Crabbox: path traversal enables arbitrary file wipe7.10.1%crabboxMay 11HIGHECVE-2026-45223Crabbox: coordinator auth bypass via forged admin claim8.80.4%crabboxMay 11HIGHCVE-2026-31253flash-attention: RCE via unsafe checkpoint deserialization7.30.2%flash_attnMay 11UNKNCVE-2026-31252CosyVoice: RCE via unsafe torch.load() deserialization—0.1%—May 11UNKNCVE-2026-31251CosyVoice: RCE via unsafe torch.load() deserialization—0.2%—May 11UNKNCVE-2026-31250CosyVoice: RCE via unsafe torch.load() in model averaging—0.2%—May 11UNKNCVE-2026-31249CosyVoice: insecure deserialization RCE via .pt files—0.2%—May 11HIGHECVE-2026-44346BentoML: Dockerfile injection enables build-time RCE8.80.3%bentomlMay 11HIGHECVE-2026-44345BentoML: unsanitized base_image allows Dockerfile RCE8.80.3%bentomlMay 11HIGHECVE-2026-44570open-webui: IDOR exposes cross-user AI memory data8.30.3%open-webuiMay 11MEDIECVE-2026-44571open-webui: auth bypass allows message tampering6.50.3%open-webuiMay 11HIGHECVE-2026-44569Open WebUI: IDOR enables cross-user message tampering7.10.3%open-webuiMay 11HIGHECVE-2026-44565open-webui: path traversal enables file write/delete8.10.5%open-webuiMay 11HIGHGHSA-6xcp-7mpr-m7wmopen-webui: CORS misconfiguration enables 1-click RCE8.3—open-webuiMay 11HIGHCVE-2026-44340PraisonAI: tar symlink bypass allows arbitrary file write7.50.4%PraisonAIMay 11HIGHECVE-2026-44339praisonaiagents: tool bypass enables undeclared callable exec8.60.4%PraisonAIMay 11CRITECVE-2026-44336PraisonAI: MCP path traversal escalates to full RCE9.60.6%PraisonAIMay 11MEDIECVE-2026-44337PraisonAI: SQL/CQL injection in knowledge-store backends6.30.2%PraisonAIMay 11HIGHECVE-2026-44338PraisonAI: unauthenticated API triggers agent workflows7.332.6%PraisonAIMay 11MEDIECVE-2022-50949Videos sync PDF: stored XSS via unsanitized media fields6.40.2%—May 10Frequently 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