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 2346 results — no patch CVE-2026-10128 Langflow: built-in component leaks server env vars 6.5 0.2% langflow Aug 5 HIGH CVE-2026-9081 Langflow: SSRF in Ollama config hits internal hosts 7.1 0.2% Langflow OSS Aug 5 MEDI CVE-2026-7657 Langflow: SSRF bypass exposes internal network/cloud data 6.5 0.2% Langflow OSS Aug 5 HIGH CVE-2026-17625 Langflow: RCE via authenticated OS command injection 7.2 0.8% Langflow OSS Aug 5 HIGH CVE-2026-9077 Langflow: MCP config write bypasses localhost restriction 8.5 0.3% langflow Aug 5 HIGH CVE-2026-8446 Langflow: OAuth auth bypass on MCP composer endpoint 7.5 0.3% langflow Aug 5 MEDI CVE-2026-7646 Langflow: path traversal via MCP leaks JWT secret 6.5 0.3% langflow Aug 5 HIGH CVE-2026-17630 Langflow: RCE via improper config parameter validation 8.8 0.4% langflow Aug 5 HIGH CVE-2026-17626 Langflow: Docker MCP volume-mount flaw exposes host files 8.8 0.3% langflow Aug 5 HIGH CVE-2026-17623 Langflow: MCP config command injection allows RCE 8.8 1.0% langflow Aug 5 HIGH E CVE-2026-67623 Mistral Vibe: RCE via malicious git fsmonitor hook 8.8 0.5% mistral-vibe Aug 5 HIGH CVE-2026-71281 peft: unsafe torch.load in LoRA-GA/CorDA allows RCE 8.8 0.3% peft Aug 5 HIGH CVE-2026-71211 MLflow AI Gateway: SSRF via unvalidated api_base 7.1 0.3% mlflow Aug 5 HIGH CVE-2026-6639 AIWU WP Plugin: unauth leak of stored OpenAI keys 7.5 0.4% — Aug 5 UNKN E CVE-2026-70470 Flowise: Unicode homoglyph bypass enables RCE — 0.9% Flowise Aug 4 UNKN E CVE-2026-69264 Flowise: CSV Agent template injection enables host RCE — 1.2% Flowise Aug 4 MEDI CVE-2026-47487 Triton Inference Server: path traversal via MLflow plugin 4.4 0.2% — Aug 4 MEDI CVE-2026-67618 marimo: PEP-723 config injection steals API keys 6.5 0.2% — Aug 4 MEDI E CVE-2026-18766 core-php-admin-panel: SQL injection via filter_col param 6.3 0.2% core-php-admin-panel Aug 4 MEDI E CVE-2026-16056 Contest Gallery WP: broken auth leaks OpenAI prompts 4.3 0.2% — Aug 4 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