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 2346 results — no patch CVE-2025-61164 Cohere North: WebSocket leak exposes session data 7.5 0.3% — Aug 26 CRIT E CVE-2025-61163 Cohere North AI: missing Origin check enables CSWSH 9.8 0.3% — Aug 26 HIGH CVE-2025-61162 Cohere North AI: IDOR allows overwriting any user record 7.5 0.2% — Aug 26 MEDI E CVE-2026-14212 Booking Calendar: IDOR enables employee account takeover 4.7 0.3% — Aug 26 LOW CVE-2026-9805 InsydeH2O: SMM buffer overflow in IHISI FMTS handler 2.7 0.1% InsydeH2O Aug 26 MEDI CVE-2026-79785 X-AnyLabeling: MITM model swap yields RCE via torch.load 5.9 0.2% — Aug 25 HIGH CVE-2026-79784 Vocos: RCE via unrestricted class loading in model config 8.8 0.3% — Aug 25 HIGH E CVE-2026-55580 mcp-shell: insecure defaults allow full shell RCE — 0.2% — Aug 25 HIGH E CVE-2026-55581 mcp-shell: bash allowlist bypass grants RCE, no auth 8.4 0.3% — Aug 25 HIGH E CVE-2026-55582 mcp-shell: secure mode bypass via git alias RCE 8.4 0.2% — Aug 25 MEDI E CVE-2026-79672 Ech0: scope bypass exposes comment admin endpoints 5.5 0.2% — Aug 25 HIGH E CVE-2026-79667 Ech0: scoped admin token bypass exposes full DB export 7.6 0.2% — Aug 25 MEDI CVE-2026-78684 vLLM: unauthenticated DoS via DeepStream decode bypass 5.3 0.3% vllm Aug 25 HIGH CVE-2026-77567 Filament: recovery codes bypass app-based MFA 8.1 0.3% — Aug 24 HIGH E CVE-2026-76073 Label Studio: IDOR exposes cross-org annotations 8.8 0.3% label-studio Aug 24 CRIT CVE-2026-71914 DrayTek VigorAP: pre-auth UDP command injection to root 9.8 3.1% — Aug 24 HIGH E CVE-2026-76841 Xinference: RCE via forced trust_remote_code=True 8.8 0.7% — Aug 24 MEDI CVE-2026-76845 adm-zip: arbitrary file overwrite via symlink extraction 6.5 0.1% adm-zip Aug 24 HIGH CVE-2026-19200 Velociraptor: NOTEBOOK_EDIT users can overwrite artifacts 8.9 0.2% — Aug 24 MEDI E CVE-2026-78205 BentoML: SSRF via unfiltered CGNAT range 5.8 0.3% bentoml Aug 24 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