AI Security Threat Feed
Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 435 results — High severity, Active exploitationtext-generation: DoS causes service disruption
CVE-2026-0599 mlflow: security flaw enables exploitation
CVE-2025-10279 agpt: Code Injection enables RCE
CVE-2026-24780 vllm: SSRF allows internal network access
CVE-2026-24779 pytorch: Code Injection enables RCE
CVE-2026-24747 langflow: security flaw enables exploitation
CVE-2026-0770 typebot: XSS enables session hijacking
CVE-2025-65098 ollama: Input Validation flaw enables exploitation
CVE-2025-66960 ollama: Input Validation flaw enables exploitation
CVE-2025-66959 chainlit: SSRF allows internal network access
CVE-2026-22219 ollama: security flaw enables exploitation
CVE-2025-15514 langchain: security flaw enables exploitation
CVE-2024-58340 llamaindex: Resource Exhaustion enables DoS
CVE-2024-58339 llamaindex: Deserialization enables RCE
CVE-2024-14021 label-studio: XSS enables session hijacking
CVE-2026-22033 vllm: Resource Exhaustion enables DoS
CVE-2026-22773 fickling: Deserialization enables RCE
CVE-2026-22612 fickling: Allowlist Bypass evades input filtering
CVE-2026-22609 fickling: Allowlist Bypass evades input filtering
CVE-2026-22608 fickling: Allowlist Bypass evades input filtering
CVE-2026-22607 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
AI Threat Alert