AI Threat Alert
AI 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 1580 results — no patch CVE-2026-35631 OpenClaw: auth bypass on ACP mutating commands 6.5 0.2% OpenClaw Apr 9 MEDI CVE-2026-35628 OpenClaw: webhook brute-force bypasses AI agent auth 4.8 0.3% OpenClaw Apr 9 MEDI CVE-2026-35627 OpenClaw: pre-auth DoS via Nostr DM resource exhaustion 6.5 0.5% OpenClaw Apr 9 MEDI CVE-2026-35626 OpenClaw: unauthenticated DoS via webhook body buffering 5.3 0.5% OpenClaw Apr 9 HIGH CVE-2026-35625 OpenClaw: privilege escalation to RCE via silent reconnect 7.8 0.2% OpenClaw Apr 9 MEDI CVE-2026-35624 OpenClaw: auth bypass exposes protected Talk rooms 4.2 0.2% OpenClaw Apr 9 MEDI CVE-2026-35623 OpenClaw: Brute-force auth bypass via webhook rate limit miss 4.8 0.4% OpenClaw Apr 9 MEDI CVE-2026-35622 OpenClaw: auth bypass in Google Chat webhook 5.9 0.3% OpenClaw Apr 9 MEDI CVE-2026-35618 OpenClaw: Plivo V2 replay bypass allows unauth actions 6.5 0.3% OpenClaw Apr 9 MEDI CVE-2026-35617 OpenClaw: auth bypass via group policy name collision 4.2 0.2% OpenClaw Apr 9 HIGH CVE-2026-34512 OpenClaw: improper authz allows admin session kill 8.1 0.3% OpenClaw Apr 9 MEDI CVE-2026-40087 LangChain: template injection leaks object attributes 5.3 0.3% langchain-core Apr 9 HIGH CVE-2026-39974 n8n-MCP: SSRF exposes cloud metadata via MCP headers 8.5 0.3% — Apr 9 MEDI CVE-2026-40037 OpenClaw: request body replay leaks credentials via redirect 6.5 0.2% OpenClaw Apr 8 MEDI E CVE-2026-5803 openai-realtime-ui: SSRF in API proxy endpoint 6.3 0.2% — Apr 8 MEDI E CVE-2026-1163 lollms: sessions persist after password reset 4.1 0.2% lollms Apr 8 HIGH CVE-2026-3357 Langflow: deserialization RCE via FAISS component default 8.8 0.5% langflow Apr 8 MEDI CVE-2026-39398 openclaw-claude-bridge: sandbox bypass exposes CLI tools — — claude-code Apr 8 HIGH E CVE-2026-35485 text-generation-webui: unauthenticated path traversal file read 7.5 0.7% gradio Apr 7 CRIT E CVE-2026-35022 Claude Code: OS command injection, credential theft 9.8 0.6% — Apr 6 Frequently 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