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-2026-57146PraisonAI: unauthenticated A2U event streaming exposed7.50.5%praisonaiOct 23HIGHECVE-2026-57144PraisonAI: sandbox fails open, bypassing FS/network limits8.80.2%praisonaiOct 23HIGHECVE-2026-57142PraisonAI: recipe policy bypass self-approves shell tool7.80.2%praisonaiOct 23HIGHCVE-2026-57121PraisonAI: missing ownership check lets members delete data8.10.3%praisonaiOct 23HIGHECVE-2026-57117PraisonAI: shell injection in agent file tools allows RCE8.80.6%praisonaiOct 23CRITECVE-2026-57116PraisonAI: unauthenticated AgentOS chat API drives agents9.80.4%praisonaiOct 23HIGHECVE-2026-57114PraisonAI: SSRF via webhook DNS rebinding bypass7.20.3%praisonaiOct 23HIGHCVE-2026-57113PraisonAI: path traversal in template cache deletes dirs8.10.4%praisonaiOct 23LOWCVE-2026-115749hydra-ray-launcher: arbitrary module import via resolver3.30.2%rayOct 23HIGHECVE-2026-56840PraisonAI: stored XSS in approval dashboard forces tool approval8.80.4%PraisonAIOct 23HIGHECVE-2026-56838PraisonAI: recipe run_stream skips dangerous-tool policy7.80.1%PraisonAIOct 23HIGHCVE-2026-56837PraisonAI: missing webhook auth lets forged Linear events drive agent8.60.2%PraisonAIOct 23HIGHECVE-2026-56836PraisonAI: unauthenticated recipe server exposes admin8.20.3%PraisonAIOct 23HIGHECVE-2026-56835PraisonAI: Slack app_mention bypasses access policy8.30.2%PraisonAIOct 23HIGHECVE-2026-56834PraisonAI: path traversal in artifact tools leaks files7.50.4%PraisonAIOct 23HIGHCVE-2026-56833PraisonAI: path traversal exposes agent logs/history7.50.5%PraisonAIOct 23HIGHECVE-2026-56832PraisonAI: Discord approval bypass allows tool call hijack8.80.1%PraisonAIOct 23CRITCVE-2026-107685req_llm: TLS verification disabled in OpenAI WebSockets—0.3%openaiOct 23CRITCVE-2026-114612LiteLLM: forged admin token enables RCE via MCP stdio9.90.3%litellmOct 22HIGHCVE-2026-115513OpenCATS: stored XSS in MRU panel enables admin takeover8.70.3%—Oct 22Frequently 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