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 2358 results — no patch CVE-2026-32049 OpenClaw: media limit bypass enables memory exhaustion DoS 7.5 0.5% OpenClaw Mar 21 HIGH CVE-2026-32048 OpenClaw: sandbox escape via cross-agent spawn bypass 7.5 0.3% OpenClaw Mar 21 MEDI CVE-2026-32046 OpenClaw: sandbox bypass enables host code execution 5.3 0.3% OpenClaw Mar 21 MEDI CVE-2026-32045 OpenClaw: auth bypass exposes HTTP gateway routes 5.9 0.4% OpenClaw Mar 21 MEDI CVE-2026-32044 OpenClaw: archive safety bypass causes DoS in skill install 5.5 0.1% OpenClaw Mar 21 MEDI CVE-2026-32043 OpenClaw: TOCTOU symlink bypasses command approval guard 6.5 0.1% OpenClaw Mar 21 HIGH CVE-2026-32042 OpenClaw: privilege escalation via unpaired device identity 8.8 0.4% OpenClaw Mar 21 HIGH E CVE-2026-23536 Feast: unauth path traversal leaks any file 7.5 1.9% rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel9 Mar 20 HIGH CVE-2026-33053 langflow: IDOR enables unauthorized data access 8.8 0.4% langflow Mar 20 MEDI CVE-2026-32041 OpenClaw: auth bypass exposes browser-control RCE 6.9 0.1% OpenClaw Mar 19 MEDI CVE-2026-32040 OpenClaw: XSS via HTML export mimeType injection 4.6 0.1% OpenClaw Mar 19 MEDI CVE-2026-32039 OpenClaw: auth bypass grants privileged tool access 5.9 0.2% OpenClaw Mar 19 CRIT CVE-2026-32038 OpenClaw: sandbox bypass enables container lateral movement 9.8 0.3% OpenClaw Mar 19 MEDI CVE-2026-32037 OpenClaw: SSRF bypass via MSTeams redirect chain 6.0 0.2% OpenClaw Mar 19 MEDI CVE-2026-32036 OpenClaw: auth bypass via encoded path traversal in gateway 6.5 0.4% OpenClaw Mar 19 MEDI CVE-2026-32035 OpenClaw: auth bypass grants owner-level tool access 5.9 0.1% OpenClaw Mar 19 HIGH CVE-2026-32034 OpenClaw: auth bypass enables high-privilege agent control 8.1 0.4% OpenClaw Mar 19 MEDI CVE-2026-32033 OpenClaw: path traversal leaks files outside workspace 6.5 0.3% OpenClaw Mar 19 HIGH CVE-2026-32032 OpenClaw: SHELL env var injection enables local RCE 7.8 0.1% OpenClaw Mar 19 MEDI CVE-2026-32031 OpenClaw: auth bypass in plugin channel gateway 4.8 0.2% OpenClaw Mar 19 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