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 852 results — Medium severity GHSA-h2vw-ph2c-jvwf OpenClaw: env injection exposes MiniMax API key — — openclaw Apr 25 MEDI GHSA-mj59-h3q9-ghfh openclaw: env var injection via MCP stdio config — — openclaw Apr 25 MEDI GHSA-hxvm-xjvf-93f3 openclaw: env namespace injection steers agent runtime — — openclaw Apr 25 MEDI GHSA-72q8-jcmc-97wx openclaw: DM policy bypass via Feishu card-action callbacks — — openclaw Apr 25 MEDI GHSA-2xcp-x87w-q377 openclaw: session key auth bypass in webhook routing — — openclaw Apr 25 MEDI GHSA-wg4g-395p-mqv3 n8n-mcp: credential exposure via HTTP transport logging 4.3 — n8n-mcp Apr 25 MEDI CVE-2026-41481 LangChain: SSRF redirect bypass exposes internal endpoints 6.5 0.2% langchain Apr 24 MEDI CVE-2026-6393 BetterDocs: Auth bypass drains OpenAI API quota 4.3 0.3% — Apr 24 MEDI CVE-2026-41495 n8n-mcp: bearer tokens exposed in HTTP transport logs 5.3 0.3% n8n-mcp Apr 23 MEDI CVE-2026-39378 nbconvert: path traversal exfiltrates files via HTML export 6.5 0.3% nbconvert Apr 21 MEDI CVE-2026-39377 nbconvert: path traversal enables arbitrary file write 6.5 0.3% nbconvert Apr 21 MEDI E CVE-2026-6608 FastChat: control flow flaw corrupts arena comparison 5.3 0.3% fschat Apr 20 MEDI E CVE-2026-6599 Langflow: MCP config injection via X-Forwarded-For header 6.3 0.2% langflow Apr 20 MEDI E CVE-2026-6598 Langflow: cleartext auth storage exposes API keys 4.3 0.2% langflow Apr 20 MEDI GHSA-f934-5rqf-xx47 OpenClaw: path traversal in memory_get reads arbitrary workspace files — — openclaw Apr 17 MEDI CVE-2026-35603 Claude Code: config hijack via unprotected ProgramData dir — 0.1% @anthropic-ai/claude-code Apr 17 MEDI GHSA-f7fh-qg34-x2xh openclaw: CDP SSRF enables internal host pivot — — openclaw Apr 17 MEDI GHSA-jhpv-5j76-m56h OpenClaw: auth bypass leaks host files via media path — — openclaw Apr 17 MEDI GHSA-536q-mj95-h29h openclaw: SSRF bypass via browser navigation guard gap — — openclaw Apr 17 MEDI GHSA-qmwg-qprg-3j38 openclaw: CDP pivot bypasses file:// navigation guards — — openclaw Apr 17 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