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 1321 results — High severity CVE-2026-41523 vLLM: assert bypass → RCE via poisoned HuggingFace model 7.5 0.7% vllm Jun 16 HIGH E CVE-2026-33760 Langflow: IDOR exposes cross-user LLM data and deletion 8.8 0.4% langflow Jun 16 HIGH E CVE-2026-54293 NLTK: path traversal leaks arbitrary local files 7.5 0.6% nltk Jun 16 HIGH CVE-2026-53721 Nuxt: auth bypass via URL case-sensitivity mismatch — 0.3% nuxt Jun 16 HIGH CVE-2026-53836 OpenClaw: PowerShell allowlist bypass enables arbitrary RCE 8.8 0.5% OpenClaw Jun 12 HIGH CVE-2026-53834 OpenClaw: auth bypass in QQBot pre-dispatch commands 7.5 0.2% OpenClaw Jun 12 HIGH CVE-2026-53833 OpenClaw: auth bypass allows agent config mutation 7.7 0.2% openclaw Jun 12 HIGH CVE-2026-53832 OpenClaw: identity header spoof grants operator access 7.7 0.1% OpenClaw Jun 12 HIGH CVE-2026-53831 OpenClaw: safe-bin allowlist bypass via shell expansion 8.3 0.2% OpenClaw Jun 12 HIGH CVE-2026-53829 OpenClaw: approval truncation bypasses exec oversight 8.0 0.2% OpenClaw Jun 12 HIGH CVE-2026-53828 OpenClaw: auth bypass enables owner command execution 8.8 0.3% OpenClaw Jun 12 HIGH CVE-2026-53823 OpenClaw: privilege escalation via Slack display name spoofing 8.1 0.2% OpenClaw Jun 12 HIGH CVE-2026-53822 OpenClaw: TOCTOU command injection bypasses allowlist 8.8 1.0% OpenClaw Jun 12 HIGH CVE-2026-53821 OpenClaw: auth bypass grants admin RPC via WebSocket 8.8 0.3% OpenClaw Jun 12 HIGH E CVE-2026-45833 ChromaDB: RCE via trust_remote_code in collection update 8.8 0.3% chromadb Jun 12 HIGH CVE-2026-45832 ChromaDB: V1 auth bypass exposes all tenant collections 8.8 0.3% chromadb Jun 12 HIGH CVE-2026-45831 ChromaDB: RBAC bypass enables cross-tenant data access 8.8 0.2% chromadb Jun 12 HIGH CVE-2026-45830 ChromaDB: auth bypass exposes any tenant's collections 8.8 0.3% chromadb Jun 12 HIGH E CVE-2026-48146 Budibase: SSRF in OAuth2 exposes cloud credentials 7.7 0.2% @budibase/server Jun 12 HIGH CVE-2026-53819 OpenClaw: RCE via workspace .env executable override 8.8 0.3% openclaw Jun 11 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