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 1961 results — Active exploitationCVE-2026-47414praisonai-platform: IDOR cross-workspace label tampering7.60.4%praisonai-platformMay 29HIGHECVE-2026-47406praisonai-platform: IDOR enables cross-workspace data poisoning8.10.4%praisonai-platformMay 29CRITECVE-2026-47410praisonai-platform: hardcoded JWT → full account takeover9.80.4%praisonai-platformMay 29HIGHECVE-2026-47405PraisonAI Platform: member self-promotes to workspace owner8.80.4%praisonai-platformMay 29HIGHECVE-2026-47399praisonai-platform: IDOR breaks workspace tenant isolation8.80.4%praisonai-platformMay 29CRITECVE-2026-47407praisonai-platform: IDOR enables cross-tenant agent hijack—0.3%praisonai-platformMay 29MEDIECVE-2026-47408praisonai-platform: IDOR exposes cross-tenant activity logs6.50.3%praisonai-platformMay 29HIGHECVE-2026-48169praisonai-platform: IDOR allows full workspace takeover8.80.4%praisonai-platformMay 29HIGHECVE-2026-47397PraisonAI: arbitrary file write via hidden webpage metadata—0.5%PraisonAIMay 29CRITECVE-2026-47391PraisonAI: Unauth RCE via A2A eval injection9.81.5%PraisonAIMay 29UNKNECVE-2026-47394PraisonAI: MCP path traversal exfiltrates host credentials—0.5%PraisonAIMay 29CRITECVE-2026-47392praisonaiagents: RCE via Python sandbox bypass9.90.9%PraisonAIMay 29MEDIECVE-2026-47395PraisonAI: SSRF via @url mention exposes localhost services5.50.2%PraisonAIMay 29CRITECVE-2026-47393PraisonAI: auth bypass in deployed API exposes LLM + tools9.80.6%PraisonAIMay 29CRITECVE-2026-47396PraisonAI: fail-open auth exposes remote agent control API9.80.4%PraisonAIMay 29MEDIECVE-2026-47390PraisonAI: SSRF bypass via loopback alias encodings5.50.2%PraisonAIMay 29HIGHECVE-2026-47398PraisonAI: RCE via ungated exec_module in agent config8.10.5%PraisonAIMay 29MEDIECVE-2026-47213BoxLite: sandbox timeout bypass enables DoS via SIGALRM6.50.3%boxliteMay 29HIGHECVE-2026-41236Froxlor: symlink-following grants customer root SSH access8.80.4%froxlor/froxlorMay 29HIGHECVE-2026-41235Froxlor: shell whitelist bypass grants host shell access—0.2%froxlor/froxlorMay 29Frequently 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