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-2026-46480Flowise: mass-assignment allows cross-workspace takeover8.80.3%flowiseJun 8HIGHECVE-2026-46479Flowise: mass assignment cross-workspace takeover8.80.3%flowiseJun 8HIGHECVE-2026-46478Flowise: mass-assignment allows cross-workspace data takeover8.80.3%flowiseJun 8HIGHECVE-2026-46477Flowise: mass-assignment cross-workspace dataset takeover8.80.3%flowiseJun 8HIGHECVE-2026-46476Flowise: mass assignment enables cross-workspace takeover8.80.3%flowiseJun 8HIGHECVE-2026-46475Flowise: mass-assignment enables workspace takeover8.80.3%flowiseJun 8CRITECVE-2026-46442Flowise: sandbox escape enables authenticated RCE9.933.0%flowiseJun 8CRITECVE-2026-46441Flowise: mass assignment breaks multi-tenant isolation9.60.3%flowiseJun 8CRITECVE-2026-46440Flowise: plaintext auth brute-force, no rate limit9.10.2%flowiseJun 8HIGHECVE-2026-47419praisonai-platform: IDOR enables cross-workspace agent read/write/delete8.30.3%praisonai-platformJun 5MEDIECVE-2026-47250mcp-server-kubernetes: flag injection steals K8s tokens6.10.4%mcp-server-kubernetesJun 5MEDIECVE-2026-11326OpenAI Atlas: XSS enables browser history exfiltration—0.2%—Jun 5HIGHECVE-2026-10814Milvus: weak hash allows RBAC grantee impersonation7.00.1%milvusJun 4LOWECVE-2026-10813LMCache: weak hash enables KV cache integrity bypass3.60.1%lmcacheJun 4MEDIECVE-2026-10804Streamlit: weak hash enables cache integrity bypass4.70.1%streamlitJun 4LOWECVE-2026-10803MLflow: weak dataset hash allows integrity bypass3.60.1%mlflowJun 4LOWECVE-2026-10801ms-swift: weak hash enables image cache poisoning3.60.1%ms-swiftJun 4LOWECVE-2026-10783Gradio: weak hash exposes audio cache to local users2.50.1%gradioJun 4UNKNECVE-2026-44182Enterprise Gateway: YAML injection → K8s cluster takeover—0.6%jupyter_enterprise_gatewayJun 3UNKNECVE-2026-44181Enterprise Gateway: SSTI allows full K8s cluster compromise—0.8%jupyter_enterprise_gatewayJun 3Frequently 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