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 1579 results — no patch CVE-2026-33574 OpenClaw: TOCTOU path traversal enables arbitrary file write 6.2 0.1% OpenClaw Mar 29 HIGH CVE-2026-33573 OpenClaw: workspace boundary bypass, arbitrary exec 8.8 0.3% OpenClaw Mar 29 HIGH CVE-2026-33572 OpenClaw: insecure transcript files expose agent secrets 8.4 0.1% OpenClaw Mar 29 CRIT CVE-2026-32987 OpenClaw: bootstrap code replay escalates to operator.admin 9.8 0.4% OpenClaw Mar 29 HIGH CVE-2026-32980 OpenClaw: unauthenticated webhook DoS via body buffering 7.5 0.5% OpenClaw Mar 29 HIGH CVE-2026-32979 OpenClaw: TOCTOU race enables local code execution 7.3 0.1% OpenClaw Mar 29 HIGH CVE-2026-32978 OpenClaw: script approval bypass allows RCE 8.0 0.2% OpenClaw Mar 29 CRIT CVE-2026-32975 OpenClaw: auth bypass via group name spoofing in agent 9.8 0.3% OpenClaw Mar 29 HIGH CVE-2026-32974 OpenClaw: auth bypass triggers forged webhook tool execution 8.6 0.2% OpenClaw Mar 29 CRIT CVE-2026-32973 OpenClaw: exec allowlist bypass enables RCE 9.8 0.4% OpenClaw Mar 29 HIGH CVE-2026-32972 OpenClaw: auth bypass enables persistent CDP backdoor 7.1 0.3% OpenClaw Mar 29 CRIT CVE-2026-32924 OpenClaw: auth bypass via Feishu reaction misclassification 9.8 0.3% OpenClaw Mar 29 MEDI CVE-2026-32923 OpenClaw: auth bypass enables Discord reaction context injection 5.4 0.2% OpenClaw Mar 29 CRIT CVE-2026-32922 OpenClaw: privilege escalation to RCE via token scope bypass 9.9 0.5% OpenClaw Mar 29 MEDI CVE-2026-32919 OpenClaw: auth bypass enables unauthorized session reset 6.1 0.1% OpenClaw Mar 29 HIGH CVE-2026-32918 OpenClaw: session sandbox escape exposes cross-agent state 8.4 0.1% OpenClaw Mar 29 HIGH CVE-2026-32915 OpenClaw: sandbox bypass enables sibling agent hijack 8.8 0.1% OpenClaw Mar 29 HIGH CVE-2026-32914 OpenClaw: access control bypass in config/debug handlers 8.8 0.3% OpenClaw Mar 29 LOW E CVE-2026-4993 OpenUI: hard-coded LiteLLM master key credential leak 3.3 0.1% — Mar 28 MEDI GHSA-h8r8-wccr-v5f2 DOMPurify: mXSS bypass achieves XSS via parse-context switch — — — Mar 27 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