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 424 results — Critical severity CVE-2026-25879 langroid: Prompt-to-SQL injection enables RCE on DB host 9.8 0.6% langroid May 27 CRIT CVE-2026-7524 Langflow: RCE via symlink traversal in archive extraction 9.8 0.8% langflow May 27 CRIT E CVE-2026-2651 MLflow: auth bypass on artifact uploads enables RCE 9.0 0.3% mlflow/mlflow May 25 CRIT E CVE-2026-46695 Boxlite: read-only bypass enables host code execution 10.0 0.3% boxlite-cli May 21 CRIT E CVE-2026-46339 9router: unauthenticated RCE exposes LLM API keys 10.0 2.4% 9router May 19 CRIT GHSA-3875-8gcx-7v46 n8n: SSRF bypasses credential domain restrictions 9.1 — n8n May 19 CRIT CVE-2026-45758 guardrails-ai: malicious 0.10.1 enables host compromise 9.6 0.3% guardrails-ai May 19 CRIT CVE-2026-2586 GlassFish: authenticated RCE via admin console 9.1 0.8% org.glassfish.jsftemplating:jsftemplating May 19 CRIT E CVE-2026-2611 MLflow: cross-origin bypass enables RCE via AI agent 9.6 0.4% mlflow May 19 CRIT GHSA-wx9m-wx4f-4cmg mistralai 2.4.6: supply chain dropper executes on import 9.6 — mistralai May 18 CRIT E CVE-2026-45829 ChromaDB: pre-auth RCE via trust_remote_code injection 10.0 12.4% chromadb May 18 CRIT E CVE-2026-45311 deepseek-tui: prompt injection enables zero-approval RCE 9.6 0.4% deepseek-tui May 14 CRIT E CVE-2026-8634 Crabbox: env-var allowlist leaks secrets to remote exec 9.1 0.7% crabbox May 14 CRIT CVE-2026-44792 n8n: SQL injection via poisoned Source Control git repo 9.0 0.3% n8n May 14 CRIT CVE-2026-44791 n8n: XML node patch bypass enables host RCE 9.9 0.6% n8n May 14 CRIT CVE-2026-44789 n8n: prototype pollution in HTTP node enables RCE 9.9 0.9% n8n May 14 CRIT GHSA-9rvc-vf7m-pgm2 Flowise: auth RCE via NodeVM sandbox escape — — flowise May 14 CRIT CVE-2026-31233 guardrails-ai: RCE via malicious Hub package manifest 9.8 0.6% guardrails-ai May 12 CRIT CVE-2026-31239 mamba: RCE via unsafe torch.load() on model load 9.8 0.4% mamba-ssm May 12 CRIT CVE-2026-31238 Ludwig: RCE via unsafe pickle deserialization in model serve 9.8 0.5% ludwig May 12 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