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 4307 resultsCVE-2026-100570OpenClaw: env injection via workspace .env allows code exec7.80.1%openclawSep 26MEDICVE-2026-100569OpenClaw: endpoint override leaks Azure Speech key5.50.1%openclawSep 26HIGHCVE-2026-100568OpenClaw: broken access control exposes cron command jobs8.30.3%openclawSep 26HIGHCVE-2026-100567OpenClaw: DNS rebinding bypasses CDP SSRF protection8.20.3%openclawSep 26MEDICVE-2026-100566OpenClaw LINE: group allowlist inherits DM allowFrom6.50.2%openclawSep 26MEDICVE-2026-100564OpenClaw: CSV formula injection in attendance export5.40.2%openclawSep 26MEDICVE-2026-100563OpenClaw: CSV formula injection in session export5.40.2%openclawSep 26MEDICVE-2026-100562OpenClaw: authorization bypass in sessions.create5.40.2%openclawSep 26HIGHCVE-2026-100561OpenClaw: exec approval bypass enables host command execution8.00.2%openclawSep 26HIGHCVE-2026-100560OpenClaw: persistent exec approval bypass via path-only grants7.50.6%openclawSep 26HIGHCVE-2026-100559OpenClaw: escaped-newline parsing bypasses exec allowlist8.00.2%openclawSep 26HIGHCVE-2026-100558OpenClaw: WebSocket upgrade socket exhaustion DoS7.50.3%openclawSep 26HIGHCVE-2026-100557OpenClaw: skill dispatch authz bypass exposes owner tools8.30.2%openclawSep 26MEDICVE-2026-100556OpenClaw: auth bypass lets WhatsApp group users switch models6.30.3%openclawSep 26HIGHCVE-2026-100555OpenClaw: DNS rebinding SSRF in Synology Chat attachments7.10.2%openclawSep 26MEDICVE-2026-100554OpenClaw: Canvas HTTP auth persists after node revocation4.20.2%openclawSep 26MEDICVE-2026-100553OpenClaw: Feishu unpin bypasses cross-context policy4.30.2%openclawSep 26HIGHCVE-2026-100552OpenClaw: Codex runtime bypasses per-chat tool policy8.80.3%openclawSep 26HIGHCVE-2026-100551OpenClaw iOS: TLS pin bypass leaks Gateway credentials8.30.2%openclawSep 26MEDICVE-2026-100550OpenClaw: Teams allowlist bypass lets outsiders trigger agent5.40.2%openclawSep 26Frequently 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