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-2026-61438PraisonAI: RCE via broken AST sandbox in workflows7.30.3%PraisonAIJul 15HIGHECVE-2026-61436PraisonAI: missing webhook signature check spoofs agents8.60.4%PraisonAIJul 15HIGHECVE-2026-61435PraisonAI: Host header spoof bypasses agent auth8.20.5%PraisonAIJul 15HIGHECVE-2026-61433PraisonAI: code injection via unsafe config codegen7.80.2%PraisonAIJul 15HIGHECVE-2026-61430PraisonAI: DNS rebinding SSRF bypass in web_crawl8.50.3%PraisonAIJul 15HIGHECVE-2026-61427PraisonAI: MCP server auth bypass by default7.30.4%PraisonAIJul 15MEDIECVE-2026-60087PraisonAI: approval caching flaw enables file write abuse6.10.3%PraisonAIJul 15HIGHECVE-2026-56400Open WebUI: CORS misconfig + CSRF enables admin RCE8.30.5%open-webuiJul 15HIGHECVE-2026-56398Open WebUI: OAuth avatar stored XSS risks account takeover7.30.6%open-webuiJul 15MEDIECVE-2026-42447jadx-gui: HTML injection in APK Summary tab leaks IP5.00.2%—Jul 14HIGHECVE-2026-50158yutu: arbitrary file write via MCP caption-download tool7.70.2%github.com/eat-pray-ai/yutuJul 14LOWECVE-2026-12482Keras: symlink bypass enables tar path traversal3.10.3%kerasJul 14LOWECVE-2026-15605wandb: weak hash weakens artifact integrity check3.10.2%wandbJul 13HIGHECVE-2026-62240CrewAI: SSRF filter bypass via DNS rebinding7.40.5%crewaiJul 13HIGHECVE-2026-45414Decidim: JWT replay bypasses multi-tenant isolation8.50.5%decidimJul 13MEDIECVE-2026-15531HashNeRF: torch.load deserialization allows local RCE5.30.3%—Jul 13MEDIECVE-2026-15521n8n-workflow-builder: path traversal via filePath arg5.30.2%—Jul 13CRITECVE-2026-61447PraisonAI: RCE via unsandboxed LLM code execution10.015.2%praisonaiJul 11CRITECVE-2026-61445PraisonAI: AICoder root RCE via unsanitized tool calls9.90.6%praisonaiJul 11HIGHECVE-2026-61442PraisonAI Platform: workspace members bypass owner authz7.10.3%praisonai-platformJul 11Frequently 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