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 1431 results — has patchCVE-2026-55178GeoLens: IDOR leaks private datasets via AI metadata API7.50.6%geolensAug 18CRITECVE-2026-75913CodeWhale: git_show argument injection enables file write9.30.5%codewhaleAug 18HIGHECVE-2026-75858CodeWhale: rlm_eval RCE bypasses approval policy7.80.4%codewhaleAug 18HIGHCVE-2026-55839Kestra: stored XSS via crafted [[link]] flow description8.70.4%io.kestra:kestraAug 18HIGHECVE-2026-69148MLflow: missing authz check leaks private artifacts7.10.4%mlflowAug 17MEDIECVE-2026-69146MLflow: missing authZ lets users forge dataset lineage6.50.4%mlflowAug 17CRITCVE-2026-64849MLflow: unauth SSRF via webhook hits cloud metadata9.310.0%mlflowAug 17MEDIGHSA-mpwr-8vm7-h73fgo-pkcs12: PBMAC1 flaw lets wrong-password files decode——software.sslmate.com/src/go-pkcs12Aug 17HIGHGHSA-j659-8xh6-5pq5atomic-agents: unpriced models silently bypass cost cap——atomic-agents-stackAug 17MEDIECVE-2026-73560vLLM: SSRF/LFI bypass in MiMo-V2 multimodal input6.50.4%vllmAug 17MEDICVE-2026-71486vLLM: unbounded /derender inputs cause resource DoS4.30.4%vllmAug 17CRITECVE-2026-72811SiYuan: SQL injection enables cross-notebook DB access10.00.4%github.com/siyuan-note/siyuan/kernelAug 14MEDICVE-2026-73559vLLM: unbounded prompt batch triggers single-request DoS6.50.6%vllmAug 13MEDIECVE-2026-73558vLLM: integer overflow leaks other users' output5.30.4%vllmAug 13MEDICVE-2026-73557vLLM: race condition bypasses prompt-embeds tensor guard—0.2%vllmAug 13MEDIECVE-2026-73556vLLM: ReDoS in structured output stalls engine5.30.5%vllmAug 13MEDICVE-2026-73555vLLM: verbose errors leak host paths & usernames5.30.4%vllmAug 13MEDICVE-2026-55102hashi-vault-js: Vault tokens leaked via thrown errors—0.2%hashi-vault-jsAug 13MEDIECVE-2026-72808SiYuan: authZ gap leaks private PDF annotations5.80.4%github.com/siyuan-note/siyuan/kernelAug 12HIGHECVE-2026-72807SiYuan: second-order SQLi via malicious template packages8.00.3%github.com/siyuan-note/siyuan/kernelAug 12Frequently 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