AI Threat Alert
AI 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 536 results — Medium severity, no patchpicklescan: FileHandler bypass creates filesystem artifacts
CVE-2026-56304 Flowise: mass assignment enables credential hash override
CVE-2026-56276 Flowise: PII exposure via unauthenticated password reset
CVE-2026-56267 Flowise: XSS enables session hijacking in AI agent UI
CVE-2025-71331 Mercator: SSRF enables internal network RCE via gopher://
CVE-2026-49345 FFmpeg RASC: UAF in decoder crashes AI inference containers
CVE-2026-12706 PraisonAI: agent ID collision leaks system prompts
CVE-2026-56077 PraisonAI: tool approval bypass enables credential theft
CVE-2026-56074 vLLM: decompression bomb OOM via audio endpoint
CVE-2026-54233 vLLM: heap address leak enables ASLR bypass
CVE-2026-54236 vLLM: integer truncation leaks GPU memory cross-tenant
CVE-2026-53923 vllm: EXIF/tRNS preprocessing gap enables adversarial input
GHSA-8jr5-v98p-w75m vLLM: NaN/Inf bypass crashes GPU inference workers
CVE-2026-54235 vLLM: image metadata mishandling corrupts multimodal inputs
CVE-2026-12491 LangGraph SDK: path traversal bypasses proxy-layer authz
CVE-2026-48776 OpenClaw: bootstrap token replay enables scope escalation
CVE-2026-53862 OpenClaw: allowlist bypass enables arbitrary shell exec
CVE-2026-53861 OpenClaw: sender allowlist bypass via conversation metadata
CVE-2026-53860 OpenClaw: SSRF blocklist bypass via trailing-dot
CVE-2026-53859 OpenClaw: insecure permissions expose agent config
CVE-2026-53856 Frequently 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