AI Threat AlertAI 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 1431 results — has patchCVE-2026-41686@anthropic-ai/sdk: insecure file perms expose agent memory—0.1%@anthropic-ai/sdkApr 29HIGHECVE-2026-41680marked: infinite recursion DoS crashes Node.js via OOM7.50.3%markedApr 29MEDIGHSA-gfg9-5357-hv4copenclaw: path traversal exposes host files via audio embed——openclawApr 29MEDIGHSA-c28g-vh7m-fm7vopenclaw: auth bypass in owner command enforcement——openclawApr 29UNKNCVE-2026-42232n8n: XML Node prototype pollution → RCE—0.5%n8nApr 29UNKNCVE-2026-42231n8n: prototype pollution → RCE via Git node SSH—0.9%n8nApr 29UNKNCVE-2026-42235n8n: stored XSS via MCP OAuth steals agent sessions—0.3%n8nApr 29UNKNCVE-2026-42226n8n: IDOR exposes cross-user API key exfiltration—0.3%n8nApr 29UNKNCVE-2026-42234n8n: Python sandbox escape enables container RCE—0.4%n8nApr 29UNKNCVE-2026-42227n8n: IDOR leaks cross-project variables via API key—0.2%n8nApr 29UNKNCVE-2026-42236n8n: unauthenticated MCP endpoint causes memory DoS—0.5%n8nApr 29UNKNCVE-2026-42228n8n: WebSocket auth bypass hijacks AI agent workflows—0.4%n8nApr 29UNKNCVE-2026-42229n8n: SQL injection in SeaTable node leaks restricted rows—0.3%n8nApr 29UNKNCVE-2026-42230n8n: MCP OAuth open redirect enables phishing—0.2%n8nApr 29UNKNCVE-2026-42233n8n: SQL injection in Oracle node allows data exfiltration—0.3%n8nApr 29UNKNCVE-2026-42237n8n: SQL injection in Snowflake/MySQL nodes bypasses fix—0.3%n8nApr 29MEDIECVE-2026-7141vllm: uninitialized KV cache memory leaks inference data5.60.3%vllmApr 27MEDIGHSA-7jm2-g593-4qrcopenclaw: config guard bypass, persistent settings mutation——openclawApr 25MEDIGHSA-qrp5-gfw2-gxv4openclaw: tool policy bypass via bundled MCP/LSP tools——openclawApr 25MEDIGHSA-h2vw-ph2c-jvwfOpenClaw: env injection exposes MiniMax API key——openclawApr 25Frequently 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