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 3023 results CVE-2026-28500 onnx: Integrity Verification bypass enables tampering 9.1 0.3% onnx Mar 18 MEDI CVE-2026-27545 OpenClaw: symlink race bypasses agent run approval 6.1 0.1% OpenClaw Mar 18 MEDI CVE-2026-27524 OpenClaw: prototype pollution bypasses command gate 4.3 0.2% OpenClaw Mar 18 MEDI CVE-2026-27523 OpenClaw: sandbox path traversal bypasses bind isolation 6.1 0.3% OpenClaw Mar 18 MEDI CVE-2026-27522 OpenClaw: path traversal enables arbitrary file read via media actions 6.5 0.4% OpenClaw Mar 18 MEDI CVE-2026-22217 OpenClaw: $SHELL env hijack enables arbitrary code execution 6.1 0.1% OpenClaw Mar 18 HIGH CVE-2026-22181 OpenClaw: SSRF guard bypass exposes internal services 7.6 0.2% OpenClaw Mar 18 MEDI CVE-2026-22180 OpenClaw: path traversal enables arbitrary file writes 5.3 0.1% OpenClaw Mar 18 HIGH E CVE-2026-22179 OpenClaw: allowlist bypass enables arbitrary OS command exec 7.2 0.6% OpenClaw Mar 18 MEDI CVE-2026-22178 OpenClaw: ReDoS via Feishu mention metadata 6.5 0.3% OpenClaw Mar 18 HIGH CVE-2026-22175 OpenClaw: allowlist bypass lets agents run any command 7.1 0.3% OpenClaw Mar 18 MEDI CVE-2026-22174 OpenClaw: local token leak via CDP probe hijack 6.8 0.1% OpenClaw Mar 18 HIGH CVE-2026-22171 OpenClaw: path traversal allows arbitrary file write 8.2 0.3% OpenClaw Mar 18 MEDI CVE-2026-22170 OpenClaw: empty allowlist bypasses BlueBubbles DM auth 6.5 0.3% OpenClaw Mar 18 MEDI CVE-2026-22169 OpenClaw: safeBins allowlist bypass enables command exec 6.7 0.2% OpenClaw Mar 18 MEDI CVE-2026-22168 OpenClaw: cmd.exe argument smuggling evades approval log 6.5 0.4% OpenClaw Mar 18 HIGH E CVE-2026-32981 Ray Dashboard: unauthenticated path traversal file read 7.5 0.9% ray Mar 17 UNKN CVE-2026-25083 GROWI: Missing Auth allows unauthorized operations — 0.3% — Mar 16 HIGH E CVE-2025-14287 mlflow: Code Injection enables RCE 7.5 1.5% mlflow Mar 16 MEDI GHSA-5cxw-w2xg-2m8h fickling: Allowlist Bypass evades input filtering — — fickling Mar 13 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