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 4330 resultsPraisonAIAgents: SSRF exposes cloud metadata via web_crawl
CVE-2026-40150PraisonAI: arbitrary file read via unguarded skill tool
CVE-2026-40117PraisonAI: unauth WebSocket drains OpenAI API credits
CVE-2026-40116PraisonAI: arg injection injects env vars into Cloud Run
CVE-2026-40113PraisonAI: XSS via no-op HTML sanitizer in agent output
CVE-2026-40112PraisonAI: RCE via shell injection in memory hooks executor
CVE-2026-40111OpenClaw: privilege escalation via synthetic admin session scope
CVE-2026-35645OpenClaw: credential exposure via gateway channel URLs
CVE-2026-35644OpenClaw: auth bypass injects restricted agent events
CVE-2026-35642OpenClaw: scope bypass enables admin RCE via device pairing
CVE-2026-35639OpenClaw: priv escalation via trusted-proxy scope bypass
CVE-2026-35638OpenClaw: auth bypass via premature cite expansion
CVE-2026-35637OpenClaw: session isolation bypass exposes parent sessions
CVE-2026-35636OpenClaw: webhook route hijack bypasses DM access controls
CVE-2026-35635OpenClaw: auth bypass grants unauthenticated Canvas access
CVE-2026-35634OpenClaw: unbounded memory alloc DoS via crafted HTTP errors
CVE-2026-35633OpenClaw: symlink traversal enables RCE via agent config
CVE-2026-35632OpenClaw: auth bypass on ACP mutating commands
CVE-2026-35631OpenClaw: webhook brute-force bypasses AI agent auth
CVE-2026-35628OpenClaw: pre-auth DoS via Nostr DM resource exhaustion
CVE-2026-35627Frequently 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