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 1527 results — Medium severityCVE-2026-53862OpenClaw: bootstrap token replay enables scope escalation4.20.1%openclawJun 16MEDICVE-2026-53861OpenClaw: allowlist bypass enables arbitrary shell exec6.60.2%openclawJun 16MEDICVE-2026-53860OpenClaw: sender allowlist bypass via conversation metadata4.20.2%openclawJun 16MEDICVE-2026-53859OpenClaw: SSRF blocklist bypass via trailing-dot6.50.2%openclawJun 16MEDICVE-2026-53856OpenClaw: insecure permissions expose agent config5.50.1%openclawJun 16MEDICVE-2026-53854OpenClaw: privilege escalation via channel auth wildcard6.50.2%openclawJun 16MEDICVE-2026-53852OpenClaw: scope bypass allows unauthorized device access5.40.2%openclawJun 16MEDICVE-2026-53851OpenClaw: Slack reaction bypass triggers agent pipeline5.30.2%openclawJun 16MEDICVE-2026-53850OpenClaw: auth bypass allows unauthorized focus state change5.50.1%openclawJun 16MEDICVE-2026-53848OpenClaw: exec allowlist bypass via command wrappers4.30.2%openclawJun 16MEDICVE-2026-53847OpenClaw: privilege escalation via write scope bypass5.40.2%openclawJun 16MEDICVE-2026-53845OpenClaw: hook bypass enables audit/policy evasion4.30.2%openclawJun 16MEDICVE-2026-53844OpenClaw: auth bypass exposes cross-session agent memory6.50.2%openclawJun 16MEDICVE-2026-53841OpenClaw: XSS via unsafe links in exported session HTML6.10.2%openclawJun 16MEDICVE-2026-48775LangGraph SQLite: deserialization RCE at checkpoint load6.80.2%langgraphJun 16MEDIECVE-2026-47748stable-diffusion.cpp: OOB read crash via crafted .ckpt file5.50.2%—Jun 16MEDICVE-2026-54306n8n: webhook prototype pollution enables confused deputy—0.3%n8nJun 16MEDICVE-2026-54308n8n: unauthed webhook bypass hijacks AI agent workflows—0.3%n8nJun 16MEDIECVE-2026-48520Langflow: unauth file read via Shareable Playground6.10.4%langflowJun 16MEDIECVE-2026-42867Langflow: path traversal enables arbitrary file write6.50.5%langflowJun 16Frequently 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