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 481 results — Critical severity CVE-2026-87983 Mistral Vibe: quoted paths bypass file read guard — 0.4% mistral-vibe Sep 11 CRIT CVE-2026-81204 Langflow: unauthenticated RCE via code injection 9.8 0.6% langflow Sep 10 CRIT CVE-2026-79724 Langflow: unauthenticated OS command injection (CVSS 9.8) 9.8 0.5% langflow Sep 10 CRIT CVE-2026-85025 Langflow: unauth RCE via public MCP endpoints 9.8 0.4% langflow Sep 10 CRIT CVE-2026-52098 Flowise: unauthenticated RCE via prediction API endpoint 9.8 0.8% flowise Sep 10 CRIT CVE-2026-13745 Gemini CLI: RCE via malicious .env GEMINI_CLI_HOME override — 0.3% run-gemini-cli GitHub Action Sep 10 CRIT E CVE-2026-79657 NLTK: pickle allowlist bypass enables RCE — 1.2% nltk Sep 8 CRIT E CVE-2026-71428 unstructured: SSRF via url= param exposes internal APIs 9.3 0.3% unstructured Sep 3 CRIT CVE-2026-19593 Codex Desktop: Git config filter triggers sandbox-escape RCE 9.8 0.3% Codex Desktop Sep 1 CRIT E CVE-2026-19295 Langflow: auth'd RCE bypasses custom-component block 9.9 1.8% langflow Aug 28 CRIT CVE-2026-19286 Langflow: unauthenticated RCE via A2A endpoint 9.8 0.6% langflow Aug 28 CRIT E CVE-2026-55634 Pimcore: DataObject field-name injection → RCE 9.9 0.4% pimcore/pimcore Aug 28 CRIT CVE-2026-55220 Pimcore: PHP deserialization flaw enables RCE — 0.5% pimcore/pimcore Aug 28 CRIT E CVE-2026-37007 crewai-tools: Path traversal in FileWriterTool enables RCE 9.8 0.7% — Aug 27 CRIT E CVE-2026-37004 LiteLLM: unauth SSTI in /prompts/test enables RCE 9.8 0.5% litellm Aug 27 CRIT E CVE-2025-61165 Cohere North AI: file upload flaw enables RCE 9.8 0.4% — Aug 26 CRIT E CVE-2025-61163 Cohere North AI: missing Origin check enables CSWSH 9.8 0.3% — Aug 26 CRIT E CVE-2026-45018 Chainlit: unauth RCE via MCP stdio cmd injection 9.8 0.7% chainlit Aug 25 CRIT E CVE-2026-55536 PraisonAI: WebSocket auth bypass hijacks browser agent 9.1 0.3% PraisonAI Aug 25 CRIT CVE-2026-71914 DrayTek VigorAP: pre-auth UDP command injection to root 9.8 3.1% — Aug 24 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