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 resultsCVE-2026-40150PraisonAIAgents: SSRF exposes cloud metadata via web_crawl7.70.3%praisonaiagentsApr 9MEDIECVE-2026-40117PraisonAI: arbitrary file read via unguarded skill tool6.20.4%praisonaiagentsApr 9HIGHECVE-2026-40116PraisonAI: unauth WebSocket drains OpenAI API credits7.50.4%praisonaiApr 9HIGHECVE-2026-40113PraisonAI: arg injection injects env vars into Cloud Run8.40.2%praisonaiApr 9MEDIECVE-2026-40112PraisonAI: XSS via no-op HTML sanitizer in agent output5.40.2%praisonaiApr 9CRITECVE-2026-40111PraisonAI: RCE via shell injection in memory hooks executor—0.2%praisonaiagentsApr 9HIGHCVE-2026-35645OpenClaw: privilege escalation via synthetic admin session scope8.10.3%OpenClawApr 9MEDICVE-2026-35644OpenClaw: credential exposure via gateway channel URLs6.50.2%OpenClawApr 9MEDICVE-2026-35642OpenClaw: auth bypass injects restricted agent events4.30.2%OpenClawApr 9HIGHCVE-2026-35639OpenClaw: scope bypass enables admin RCE via device pairing8.80.5%OpenClawApr 9HIGHCVE-2026-35638OpenClaw: priv escalation via trusted-proxy scope bypass8.80.3%OpenClawApr 9HIGHCVE-2026-35637OpenClaw: auth bypass via premature cite expansion7.30.3%OpenClawApr 9MEDICVE-2026-35636OpenClaw: session isolation bypass exposes parent sessions6.50.3%OpenClawApr 9MEDICVE-2026-35635OpenClaw: webhook route hijack bypasses DM access controls4.80.3%OpenClawApr 9MEDICVE-2026-35634OpenClaw: auth bypass grants unauthenticated Canvas access5.10.1%OpenClawApr 9MEDICVE-2026-35633OpenClaw: unbounded memory alloc DoS via crafted HTTP errors5.30.4%OpenClawApr 9HIGHECVE-2026-35632OpenClaw: symlink traversal enables RCE via agent config7.10.4%OpenClawApr 9MEDICVE-2026-35631OpenClaw: auth bypass on ACP mutating commands6.50.2%OpenClawApr 9MEDICVE-2026-35628OpenClaw: webhook brute-force bypasses AI agent auth4.80.3%OpenClawApr 9MEDICVE-2026-35627OpenClaw: pre-auth DoS via Nostr DM resource exhaustion6.50.5%OpenClawApr 9Frequently 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