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 4307 resultsCVE-2026-55536PraisonAI: WebSocket auth bypass hijacks browser agent9.10.5%PraisonAIAug 25HIGHECVE-2026-55532PraisonAI: Origin bypass CSRF enables prompt injection7.60.2%PraisonAIAug 25HIGHECVE-2026-55533PraisonAI: auth fail-open lets unauthenticated recipe execution8.20.5%PraisonAIAug 25HIGHCVE-2026-55539PraisonAI: no-auth Jobs API allows arbitrary agent runs8.60.6%PraisonAIAug 25HIGHCVE-2026-55527PraisonAI: path traversal in agent memory allows arbitrary file write7.10.5%praisonaiagentsAug 25UNKNECVE-2026-55541PraisonAI: no auth on agent serve API (create/invoke)—0.5%PraisonAIAug 25MEDIECVE-2026-55535PraisonAI: TOCTOU SSRF in webhook validation6.80.3%PraisonAIAug 25HIGHECVE-2026-55537PraisonAI: SSRF via race condition in webhook DNS check7.10.3%PraisonAIAug 25HIGHECVE-2026-55538PraisonAI: missing auth allows agent execution7.30.4%PraisonAIAug 25HIGHECVE-2026-55540PraisonAI: symlink escape defeats workspace path checks7.10.4%PraisonAIAug 25MEDIECVE-2026-55530PraisonAI: missing authz lets agent mass-rewrite files6.10.2%praisonaiagentsAug 25HIGHECVE-2026-55534PraisonAI: API key ignored, agent endpoints unauth8.60.5%PraisonAIAug 25HIGHCVE-2026-55526PraisonAI: SSRF bypass via DNS-rebinding hostname8.50.4%praisonaiagentsAug 25MEDIECVE-2026-55531PraisonAI: unauth memory exhaustion via MCP sessions6.50.5%PraisonAIAug 25HIGHECVE-2026-55528PraisonAI: AgentServer auth token never enforced8.20.5%praisonaiagentsAug 25MEDIECVE-2026-55529PraisonAI: MCP origin-check bypass runs local tools6.90.2%PraisonAIAug 25HIGHECVE-2026-55525PraisonAI: SSRF via redirect bypasses crawl allowlist7.50.5%praisonaiagentsAug 25MEDIECVE-2026-79672Ech0: scope bypass exposes comment admin endpoints5.50.3%—Aug 25HIGHECVE-2026-79667Ech0: scoped admin token bypass exposes full DB export7.60.3%—Aug 25MEDICVE-2026-78684vLLM: unauthenticated DoS via DeepStream decode bypass5.30.6%vllmAug 25Frequently 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